# Analyst Estimates Source: https://docs.bigdata.com/api-reference/analyst-estimates/analyst-estimates /api-rest/openapi/openapi_structured_data.json post /v1/analyst-estimates/query Retrieves analyst financial estimates for a given symbol, including projected revenue, earnings per share (EPS), and other key metrics, as forecasted by industry analysts. Each request returns estimates for one company. The `results.values` array is ordered with the furthest-future forecasted period first, working backward to the oldest period returned. Forward-looking forecasts and past periods sit on the same timeline, so how much history and how far ahead analysts forecast varies by company. Coverage is densest for the next two to three years and thins out beyond that. Filtering by date range is not supported. Use `period` to choose annual or quarterly estimates and `limit` to control how many periods are returned. # Analyst Ratings Source: https://docs.bigdata.com/api-reference/analyst-estimates/analyst-ratings /api-rest/openapi/openapi_structured_data.json post /v1/analyst-ratings/query Retrieves analyst ratings and recommendations for a given symbol, including buy/hold/sell counts and the consensus recommendations. # Earnings Surprises Source: https://docs.bigdata.com/api-reference/analyst-estimates/earnings-surprises /api-rest/openapi/openapi_structured_data.json post /v1/latest-surprise/query The Earnings Surprises API allows users to retrieve the most recent quarterly earnings surprise data for a specific company. This endpoint provides actual versus estimated earnings per share (EPS) and revenue (sales), highlighting whether the company has beaten, missed, or met expectations. # Target Price Source: https://docs.bigdata.com/api-reference/analyst-estimates/target-price /api-rest/openapi/openapi_structured_data.json post /v1/price/target/query This endpoint retrieves target price for a company, including target high, target low, target consensus, and target median. # Create a Batch Job Source: https://docs.bigdata.com/api-reference/batch-search/create-a-batch-job /api-rest/openapi/openapi_search_service.json post /v1/search/batches Process large volumes of requests asynchronously with [50% lower costs](/getting-started/bigdata_api_pricing). Batch Search provides a simple set of endpoints to initiate batch processing jobs, monitor progress as requests are executed, and collect results once processing completes. Each batch begins with a `.jsonl` file where every line represents an individual Search request. Once your input file is ready, call the following endpoint to obtain a `batch_id` and `presigned_url`. Copy the `presigned_url` from the response. You will need this URL to [upload your input file](/api-reference/batch-search/upload-your-input-file). For a step-by-step walkthrough, see the [Batch Search how-to guide](/how-to-guides/search/batch_search). # Get Batch Job Info Source: https://docs.bigdata.com/api-reference/batch-search/get-batch-job-info /api-rest/openapi/openapi_search_service.json get /v1/search/batches/{batch_id} Check the status of your batch job and retrieve results when processing is complete. - `batch_id`: Your job's unique identifier - `status`: Current processing state (pending, processing, completed, failed, or cancelled) - `estimated_completion_time`: A dynamic ISO 8601 timestamp indicating when the job is expected to finish. This adjusts in real-time based on system throughput and queue backlog. - `output_file_url`: Download link for your results (available when status is completed) Once your batch reaches `completed` status, use the `output_file_url` to download a `.jsonl` file containing all results via a simple GET request. Each line in your results file contains: | Field | Type | Description | |-------|------|-------------| | line_number | int | Matches the line number from your original input file | | status | string | Result status: success, error, timeout, or exception | | query | object | The original search query you submitted | | response | object | The Search response for this query | | code | int | HTTP status code | | error | string | Error description (only present if request failed) | For a step-by-step walkthrough, see the [Batch Search how-to guide](/how-to-guides/search/batch_search). # Upload Your Input File Source: https://docs.bigdata.com/api-reference/batch-search/upload-your-input-file /api-rest/openapi/openapi_search_service.json put /s3_upload_placeholder Now that you have created your batch job, use the `presigned_url` to upload your `.jsonl` file directly to the designated storage location using the following command: ```shell curl --request PUT \ --url '' \ --header 'Content-Type: application/jsonl' \ --data-binary '@your_input_file.jsonl' ``` Replace `` with the `presigned_url` and `@your_input_file.jsonl` with the path to your actual file. For a step-by-step walkthrough, see the [Batch Search how-to guide](/how-to-guides/search/batch_search). # Connected Entities Source: https://docs.bigdata.com/api-reference/co-mentions/connected-entities /api-rest/openapi/openapi_search_service.json post /v1/search/co-mentions/entities Explore entities associated with your search filters to reveal deeper connections. This endpoint retrieves the top N entities ranked by chunk volume and headline volume, merges the two sets, and returns entities with combined or individual counts. Timestamp ranges are limited to one year; for longer periods, split into successive one-year requests. # Connected Topics Source: https://docs.bigdata.com/api-reference/co-mentions/connected-topics /api-rest/openapi/openapi_search_service.json post /v1/search/co-mentions/topics Explore topics associated with your search filters to reveal deeper connections. This endpoint retrieves the top N topics ranked by chunk volume and headline volume, merges the two sets, and returns topics with combined or individual counts. # Find by details Source: https://docs.bigdata.com/api-reference/companies/find-by-details /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/companies Bigdata.com Knowledge Graph tracks over 7 million companies worldwide. Use this endpoint to search by name, website, ticker, or other market identifiers. Refine your results with filters such as company type, country, or sector. # Get by CUSIP Source: https://docs.bigdata.com/api-reference/companies/get-by-cusip /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/companies/cusip Locate companies using Committee on Uniform Securities Identification Procedures (CUSIP) numbers, enabling coverage of both equities and fixed income instruments. # Get by ISIN Source: https://docs.bigdata.com/api-reference/companies/get-by-isin /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/companies/isin Locate companies using International Securities Identification Numbers (ISIN), enabling coverage of both equities and fixed income instruments. # Get by Listing Source: https://docs.bigdata.com/api-reference/companies/get-by-listing /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/companies/listing Locate companies using exchange listing identifiers. # Get by SEDOL Source: https://docs.bigdata.com/api-reference/companies/get-by-sedol /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/companies/sedol Locate companies using Stock Exchange Daily Official List (SEDOL) numbers. # Get sectors Source: https://docs.bigdata.com/api-reference/companies/get-sectors /api-rest/openapi/openapi_knowledge_graph.json get /v1/knowledge-graph/companies/sectors Retrieve the list of available sectors to be used as filters when searching for companies in the Knowledge Graph. The same list is returned by `GET /v1/knowledge-graph/companies/values/sectors`, which lists the values of any category filter. # Get Subsidiaries Source: https://docs.bigdata.com/api-reference/companies/get-subsidiaries /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/subsidiaries/query Returns the full subsidiary hierarchy for a given company. For each subsidiary includes: ultimate parent, immediate parent, company name, and hierarchy depth level. # Company Profile Source: https://docs.bigdata.com/api-reference/company-&-events/company-profile /api-rest/openapi/openapi_structured_data.json post /v1/company-profile/query This endpoint retrieves comprehensive company profile data including company name, sector, industry, CEO, market cap, and other key business information. # ESG Scores Source: https://docs.bigdata.com/api-reference/company-&-events/esg-scores /api-rest/openapi/openapi_structured_data.json post /v1/esg-performance-score/query The ESG Performance Score API provides a comprehensive evaluation of a company's environmental, social, and governance (ESG) practices. It aggregates various ESG metrics into a single performance score, allowing investors and stakeholders to assess the company's commitment to sustainable and responsible business operations. The ESG scores reflect companies' sustainability performance relative to financially material ESG issues. Scores are derived from standardized company-reported data and peer-based relative scoring techniques, resulting in a 0–100 scale that indicates a company's position versus its global peers, following a sector-specific, SASB (Sustainability Accounting Standards Board)-inspired materiality framework. | Performance | Score Range | |---|---| | Laggard | < 42 | | Below Average | 42 - 47 | | Average | 48 - 53 | | Above Average | 54 - 59 | | Leader | ≥ 60 | # Events Calendar Source: https://docs.bigdata.com/api-reference/company-&-events/events-calendar /api-rest/openapi/openapi_structured_data.json post /v1/events-calendar/query A financial data API that returns details of key corporate events, such as earnings calls, conference calls, US IPO listings, and US delistings. Query by a specific list of companies, by date range alone, or both, allowing investors and analysts to track upcoming and historical company announcements in real time. # Stocks & Funds Screener Source: https://docs.bigdata.com/api-reference/company-&-events/stocks-&-funds-screener /api-rest/openapi/openapi_structured_data.json post /v1/company-screener/query The Company Screener API enables advanced filtering and discovery of companies based on comprehensive financial and descriptive criteria. Filter companies by market capitalization, stock price, beta, trading volume, dividend yield, sector, industry, country, exchange, and trading status. Perfect for investment research, portfolio construction, and market analysis. # Find by details Source: https://docs.bigdata.com/api-reference/concepts/find-by-details /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/concepts Find concepts such as economic indicators, financial instruments and business terms. Search by name or description and narrow the results by type. # Create connector Source: https://docs.bigdata.com/api-reference/connectors/create-connector /api-rest/openapi/openapi_content_data.json post /contents/v1/connectors We recommend using **[Bigdata Connectors Management](https://platform.bigdata.com/connectors)** on the Developer Platform—the guided experience sets up connectors in **four simple steps**. You can also call this endpoint to register connectors programmatically. Provide the connector **type**, **label**, and type-specific **config**. For **email** connectors, an inbox is created and its address is returned; forward emails from allowed senders to that address to ingest, process and index incoming content. For **investment_research** connectors, provide broker credentials and the platform will sync research documents from the broker feed. For **sharepoint** (Microsoft SharePoint) connectors, set `"type": "sharepoint"` and supply **`config.session_id`** only. Contact [support@bigdata.com](mailto:support@bigdata.com) to know more about how to generate this parameter. # Delete connector by ID Source: https://docs.bigdata.com/api-reference/connectors/delete-connector-by-id /api-rest/openapi/openapi_content_data.json delete /contents/v1/connectors/{connector_id} By default, soft-deletes a connector: the connector is marked as archived and will no longer ingest new content; existing documents that were ingested by this connector remain available. The operation is idempotent for an already-archived connector. To permanently remove the connector and all related data, add the query parameter `force_delete=true`. This triggers a hard delete flow: all files related to this connector are deleted asynchronously. Once all files are deleted, the connector is removed from the database (final step of the async process). The deletion process is asynchronous. # Get connector by ID Source: https://docs.bigdata.com/api-reference/connectors/get-connector-by-id /api-rest/openapi/openapi_content_data.json get /contents/v1/connectors/{connector_id} Returns full details for a single connector by its UUID. Use this to inspect connector metadata and configuration. Credentials and secrets are never included in the response. # List connectors Source: https://docs.bigdata.com/api-reference/connectors/list-connectors /api-rest/openapi/openapi_content_data.json get /contents/v1/connectors Returns all connectors that belong to the authenticated user. Use this to discover connector_id values for filtering documents, for update/delete operations, or to trigger a syncronization job on demand. Connector configuration is included. Sensitive fields are never returned. # Trigger connector sync Source: https://docs.bigdata.com/api-reference/connectors/trigger-connector-sync /api-rest/openapi/openapi_content_data.json post /contents/v1/connectors/{connector_id}/sync Queues a new synchronization run for an **investment_research** or **sharepoint** connector. For **investment_research**, send a JSON body with **`date_limit`** (calendar date, `YYYY-MM-DD`) so the broker sync includes research from that date onward according to platform rules. For **sharepoint**, send an empty JSON body (`{}`). Only content not already ingested will be synced. # Update connector by ID Source: https://docs.bigdata.com/api-reference/connectors/update-connector-by-id /api-rest/openapi/openapi_content_data.json put /contents/v1/connectors/{connector_id} Update an existing connector's **label**, **description**, and **share_with_org**. For **email** connectors, you may also update **config** (e.g. `allowed_emails`). For **investment_research** and **sharepoint** connectors, configuration cannot be updated. As a PUT request, required fields follow the schema; leaving out a field can clear or default it. The connector **type** cannot be changed. # Delete document Source: https://docs.bigdata.com/api-reference/documents/delete-document /api-rest/openapi/openapi_content_data.json delete /contents/v1/documents/{content_id} Deletes a target document from the platform. It removes everything: original document, annotated version, and chunks from the vector database. # Enrich document Source: https://docs.bigdata.com/api-reference/documents/enrich-document /api-rest/openapi/openapi_content_data.json post /contents/v1/documents Request a pre-signed URL to upload a document directly to Bigdata.com. The response contains a single-use url and the document id. Send a **PUT request** to that URL with the document file as the body to complete the upload. Bigdata then **enriches** the document (extraction, structure and annotation of the content). By default it is also **indexed** and becomes available for the Search and Research Agent. Set **`no_index`** to skip indexing while keeping the document stored and retrievable, or **`no_store`** to skip indexing and retain the document for only 24 hours after enrichment completes. # Get annotated document Source: https://docs.bigdata.com/api-reference/documents/get-annotated-document /api-rest/openapi/openapi_content_data.json get /contents/v1/documents/{content_id}/annotated Returns a time-limited pre-signed URL to download **private** document content in annotated (structured) JSON format. Use this only for documents you ingested via the Content API (connectors or direct upload). When you GET the URL, the response contains document content, metadata and annotations. The URL expires after 24 hours; request a new one if needed. # Get document metadata Source: https://docs.bigdata.com/api-reference/documents/get-document-metadata /api-rest/openapi/openapi_content_data.json get /contents/v1/documents/{content_id} Returns metadata for a single document by its content ID (the document id returned by List documents). Use this to check status, file_name, connector_id, tags, enrichments_requested, enrichments_applied, usage, and timestamps. To retrieve the actual file content, use Get annotated document (enriched JSON) or Get original document (original file format). # Get original document Source: https://docs.bigdata.com/api-reference/documents/get-original-document /api-rest/openapi/openapi_content_data.json get /contents/v1/documents/{content_id}/original Returns a time-limited pre-signed URL to download the **private** document's original file as uploaded (e.g. .eml, .pdf). When you GET the URL, the response is the raw file with appropriate Content-Type and Content-Disposition. Use this when you need the native format rather than the annotated JSON. The URL expires after 24 hours; request a new one if needed. # List documents Source: https://docs.bigdata.com/api-reference/documents/list-documents /api-rest/openapi/openapi_content_data.json get /contents/v1/documents Returns a paginated list of documents that the user has uploaded or that have been shared with their organization. Use the query parameters documented below for filtering. Use the returned document id with Get document, Get annotated document, or Get original document to retrieve metadata or file content. # Update document metadata Source: https://docs.bigdata.com/api-reference/documents/update-document-metadata /api-rest/openapi/openapi_content_data.json patch /contents/v1/documents/{content_id} Partially update a document's metadata. Send only the fields you want to change. - **`tags`**: Array of **tag IDs** (UUIDs) to assign to the document. This replaces the document's current tag set, so you can add or remove tags by including the full list you want applied. Each ID must refer to an existing tag (use **POST** `/contents/v1/tags` to create one, or **GET** `/contents/v1/tags` to list IDs). If any ID is invalid, the API returns `400` with error code `INVALID_TAGS_ERROR`. - **`share_with_org`**: When `true`, the document is available to all members of your organization. When `false`, only you can access it. # Get Entities by ID Source: https://docs.bigdata.com/api-reference/entities/get-entities-by-id /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/entities/id Retrieve entities by their RavenPack ID, a unique identifier used across the Bigdata.com ecosystem. Users can retrieve up to 100 entities per request. # Find by details Source: https://docs.bigdata.com/api-reference/etfs/find-by-details /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/etfs Find exchange-traded funds through a comprehensive search. Search by name, ticker, or description and filter by country to discover relevant ETFs for your investment research. # Get filter values Source: https://docs.bigdata.com/api-reference/filter-values/get-filter-values /api-rest/openapi/openapi_knowledge_graph.json get /v1/knowledge-graph/{category}/values/{filter} Retrieve every value a category filter can take, so a filter can be built without guessing its values. Values are returned in the exact form the corresponding search filter accepts: countries as ISO 3166-1 alpha-2 codes, source ranks as `RANK_1`..`RANK_5`, and so on. The full sorted list is returned; there is no narrowing parameter, and lists are capped at 5000 values. Every filter of every category is available except three on `sources`, which are stored in a way that cannot be enumerated and return 404: `packages`, `categories` and `tiers`. # Balance Sheet Source: https://docs.bigdata.com/api-reference/financials-&-ratios/balance-sheet /api-rest/openapi/openapi_structured_data.json post /v1/balance-sheet/query This endpoint retrieves fundamental balance sheet measures for a company, including assets, liabilities, and equity across reporting periods. # Cash Flow Statement Source: https://docs.bigdata.com/api-reference/financials-&-ratios/cash-flow-statement /api-rest/openapi/openapi_structured_data.json post /v1/cash-flow-statement/query This endpoint retrieves fundamental cash flow statement measures for a company, including operating, investing, and financing cash flows across reporting periods. # Company Ratios TTM Source: https://docs.bigdata.com/api-reference/financials-&-ratios/company-ratios-ttm /api-rest/openapi/openapi_structured_data.json post /v1/company-ratios-ttm/query Retrieves fundamental company ratios for a company, including revenue, expenses, and profitability metrics across reporting periods. # Income Statement Source: https://docs.bigdata.com/api-reference/financials-&-ratios/income-statement /api-rest/openapi/openapi_structured_data.json post /v1/income-statement/query This endpoint retrieves fundamental income statement measures for a company, including revenue, expenses, and profitability metrics across reporting periods. # Key Metrics TTM Source: https://docs.bigdata.com/api-reference/financials-&-ratios/key-metrics-ttm /api-rest/openapi/openapi_structured_data.json post /v1/key-metrics-ttm/query The Key Metrics TTM API provides seamless access to a comprehensive set of trailing twelve-month (TTM) performance indicators. It delivers insights into a company's profitability, capital efficiency, and liquidity, enabling in-depth evaluation of financial health and operational performance over the past year. # Revenue Geographic Segments Source: https://docs.bigdata.com/api-reference/financials-&-ratios/revenue-geographic-segments /api-rest/openapi/openapi_structured_data.json post /v1/company-revenue-geographic-segments/query The Revenue Geographic Segments API allows users to retrieve revenue data segmented by geographical regions, helping investors and analysts understand the performance of a company in different markets. # Revenue Product Segments Source: https://docs.bigdata.com/api-reference/financials-&-ratios/revenue-product-segments /api-rest/openapi/openapi_structured_data.json post /v1/company-revenue-product-segments/query The Revenue Product Segments API provides access to detailed revenue data broken down by individual products. This enables investors and analysts to gain deeper insights into a company’s performance across its product portfolio. # Fund Holdings Source: https://docs.bigdata.com/api-reference/fund-holdings/fund-holdings /api-rest/openapi/openapi_structured_data.json post /v1/holdings/funds/stocks/ Retrieve portfolio holdings disclosed by institutional funds in their SEC 13F filings. This dataset provides an overview of a fund’s positions, including the total number of holdings, overall portfolio size, and high-level summaries such as top holdings and allocation trends. It also allows retrieval of the top buys and sells for a fund or fund manager, either for the latest portfolio or for historical quarters. Sector composition of the fund’s portfolio can also be accessed. # Fund Position Signals Source: https://docs.bigdata.com/api-reference/fund-holdings/fund-position-signals /api-rest/openapi/openapi_structured_data.json post /v1/holdings/funds/trends/ Retrieve a strategic overview of top stocks based on aggregated position changes by hedge funds, utilizing data from the most recent SEC 13F filings. This endpoint provides a detailed overview of fund activities, capturing changes across calls, puts, new positions, closures, and net adjustments. It highlights where hedge funds are intensifying their focus, reducing exposure, or completely shifting their investment strategies, helping users identify trends and strategic moves in the market. # Stock Fund Holdings Source: https://docs.bigdata.com/api-reference/fund-holdings/stock-fund-holdings /api-rest/openapi/openapi_structured_data.json post /v1/holdings/stocks/funds Retrieve institutional fund holdings for a specified stock, based on the latest SEC 13F filings. The endpoint returns top holders with their current market value, share count, quarterly change, and estimated capital flow. This allows users to identify leading institutional investors, track changes in ownership, and analyze fund activity trends such as increases or reductions in positions. # Aftermarket Prices Source: https://docs.bigdata.com/api-reference/market-data/aftermarket-prices /api-rest/openapi/openapi_structured_data.json post /v1/price/aftermarket/query Returns the latest extended-hours (aftermarket) trade and quote for one or more companies. Each record includes the last aftermarket trade (price, size, timestamp) and quote (best bid/ask price and size, cumulative volume, timestamp). # Daily Prices Source: https://docs.bigdata.com/api-reference/market-data/daily-prices /api-rest/openapi/openapi_structured_data.json post /v1/price/daily/query Returns daily historical price and volume data for a given symbol. Supports stocks, ETFs, indexes, cryptocurrencies, commodities (continuous futures) and forex pairs. Each data point includes date, open, high, low, close, volume, change, change percentage, and volume-weighted average price (VWAP). Ideal for tracking daily market performance and conducting technical analysis over extended periods. # Dividends Source: https://docs.bigdata.com/api-reference/market-data/dividends /api-rest/openapi/openapi_structured_data.json post /v1/dividends/query Returns historical and upcoming dividend data for companies. Supports stocks and ETFs. Each dividend record includes ex-dividend date, record date, payment date, declaration date, dividend amount, adjusted dividend, yield, and frequency. # Entity Sentiment Source: https://docs.bigdata.com/api-reference/market-data/entity-sentiment /api-rest/openapi/openapi_structured_data.json post /v1/entity-sentiment/ Returns a time series of daily sentiment metrics for a single entity over a specified date range. Sentiment is a quantified signal derived from unstructured text using rule-based and machine-learning methods, indicating likely positive or negative market impact. The response includes daily_sentiment (mean sentiment), sentiment_pressure (abnormal sentiment intensity), and abnormal_media_attention (abnormal media volume). # Intraday Prices Source: https://docs.bigdata.com/api-reference/market-data/intraday-prices /api-rest/openapi/openapi_structured_data.json post /v1/price/intraday/query Returns intraday historical price and volume data for a given symbol at specified intervals (e.g. 1min, 5min, 15min, 30min, 1hour). Supports stocks, ETFs, commodities (continuous futures), indexes, cryptocurrencies, and forex pairs. Each data point includes timestamp, open, high, low, close, and volume. # Price Changes Source: https://docs.bigdata.com/api-reference/market-data/price-changes /api-rest/openapi/openapi_structured_data.json post /v1/price/changes/query This endpoint track price fluctuations in real-time with the Price Changes API. Monitor percentage changes over various time periods, including daily (1D), monthly (1M), yearly (1Y) and long-term (max). # Quote Source: https://docs.bigdata.com/api-reference/market-data/quote /api-rest/openapi/openapi_structured_data.json post /v1/quote/query This endpoint provides real-time asset quotes with the Quote API. Access up-to-the-minute prices, price changes, and trading volume for individual assets, ensuring you stay on top of market movements. Assets covered include stocks, cryptocurrencies, commodities, and ETFs. # Create a monitor Source: https://docs.bigdata.com/api-reference/monitors/create-a-monitor /api-rest/openapi/openapi_search_monitoring.json post /v1/search-monitoring/monitors Create a monitor with an intent and schedule. Optionally customize its name, search, extraction rules, output fields, and entity watchlist. Set `status` to `inactive` while you test the monitor, then change it to `active` when it is ready to run continuously. # Delete a monitor Source: https://docs.bigdata.com/api-reference/monitors/delete-a-monitor /api-rest/openapi/openapi_search_monitoring.json delete /v1/search-monitoring/monitors/{monitor_id} Permanently delete a monitor. To stop new runs without losing the monitor, update its status to `inactive` instead. # Get monitor details Source: https://docs.bigdata.com/api-reference/monitors/get-monitor-details /api-rest/openapi/openapi_search_monitoring.json get /v1/search-monitoring/monitors/{monitor_id} View one monitor's search, schedule, extraction rules, output fields, and status. # Get run details Source: https://docs.bigdata.com/api-reference/monitors/get-run-details /api-rest/openapi/openapi_search_monitoring.json get /v1/search-monitoring/monitors/{monitor_id}/runs/{run_id} View one run, including the period it searched, the events it found, links to supporting sources, and API usage. # List monitor runs Source: https://docs.bigdata.com/api-reference/monitors/list-monitor-runs /api-rest/openapi/openapi_search_monitoring.json get /v1/search-monitoring/monitors/{monitor_id}/runs View completed, pending, or failed runs for a monitor. Choose live or simulation runs. Set `include_events=true` to include the events found during each run. # List monitors Source: https://docs.bigdata.com/api-reference/monitors/list-monitors /api-rest/openapi/openapi_search_monitoring.json get /v1/search-monitoring/monitors View your monitors. Filter the list by status, name, or the development each monitor is designed to track. # Simulate a monitor Source: https://docs.bigdata.com/api-reference/monitors/simulate-a-monitor /api-rest/openapi/openapi_search_monitoring.json post /v1/search-monitoring/monitors/{monitor_id}/simulate Test a monitor against recent historical data without activating it. The test runs in the background. Use the returned `simulation_id` to check its progress and results. # Update a monitor Source: https://docs.bigdata.com/api-reference/monitors/update-a-monitor /api-rest/openapi/openapi_search_monitoring.json patch /v1/search-monitoring/monitors/{monitor_id} Change a monitor's name, status, search, schedule, extraction rules, output fields, or entity watchlist. Send only the fields you want to change; omitted fields stay unchanged. Set `status` to `active` to start scheduled runs or `inactive` to pause them. After changing the search, extraction rules, or output fields, run another simulation before activating the monitor. A monitor keeps the intent it was created with. If you want to track a different type of event, create another monitor. # Find by details Source: https://docs.bigdata.com/api-reference/organizations/find-by-details /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/organizations Find organizations such as central banks, regulators, government bodies and NGOs. Search by name or description and narrow the results by type, country, ultimate parent or owner. # Find by details Source: https://docs.bigdata.com/api-reference/people/find-by-details /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/people Find people such as executives, politicians and public figures. Search by name or description and narrow the results by position, employer, nationality or gender. # Find by details Source: https://docs.bigdata.com/api-reference/places/find-by-details /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/places Find places such as countries, regions, cities and facilities. Search by name or description and narrow the results by category, type, continent, country or region. # Find by details Source: https://docs.bigdata.com/api-reference/products/find-by-details /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/products Find products and brands. Search by name or description and narrow the results by product type or owner. # Get Subscription Quotas Source: https://docs.bigdata.com/api-reference/quotas/get-subscription-quotas /api-rest/openapi/openapi_subscription.json get /v1/subscription/quotas Returns the current subscription quotas and usage for the organization. For examples, see the [Monitor usage](/how-to-guides/monitor_usage) how-to guide. # Research Agent Source: https://docs.bigdata.com/api-reference/research-agent/research-agent /api-rest/openapi/openapi_research_agent.json post /v1/research-agent Execute a research query with AI-powered analysis and real-time data. Returns a streaming response via Server-Sent Events. # Fetch document Source: https://docs.bigdata.com/api-reference/search/fetch-document /api-rest/openapi/openapi_search_service.json get /v1/documents/{document_id} Returns a time-limited pre-signed URL for downloading the document in annotated (structured) JSON format. Issuing a GET request to that URL returns the document's content, metadata, and annotations. The URL expires after 24 hours; request a new one when it does. This endpoint works for any document in Bigdata, whether it originates from the RavenPack catalog or from your own processed files. When `web_content` is `true`, the returned document also includes a direct URL to the publisher's original article on the web. # Search documents Source: https://docs.bigdata.com/api-reference/search/search-documents /api-rest/openapi/openapi_search_service.json post /v1/search Easily find the most relevant information from trusted sources and your own data. Use it to power agents that give accurate, real-time answers. # Search volume Source: https://docs.bigdata.com/api-reference/search/search-volume /api-rest/openapi/openapi_search_service.json post /v1/search/volume Get document and chunk volume statistics over time for a search query, aggregated by date with sentiment analysis. # Search watchlist Source: https://docs.bigdata.com/api-reference/search/search-watchlist /api-rest/openapi/openapi_search_service.json post /v1/search/watchlist Run a query across a watchlist of entities and get the results grouped per entity. With `/v1/search` and a list of entities in an `any_of` filter, a handful of those entities can take most of the chunks. Watchlist search distributes the chunks across the watchlist instead: either a total budget spread over the entities (`max_chunks.per_entity: false`) or a fixed number of chunks for every entity (`max_chunks.per_entity: true`), so coverage of the watchlist is far more uniform. A chunk is assigned to a single entity, and results are always diversified across sources. The response carries one group per requested entity, in request order; entities without matches come back with an empty `documents` list. Billing is the same as `/v1/search`. # Find by details Source: https://docs.bigdata.com/api-reference/sources/find-by-details /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/sources Locate and explore data sources and information providers within the knowledge graph. Filter sources by country, rank, and category to find the most relevant information providers. # Create tag Source: https://docs.bigdata.com/api-reference/tags/create-tag /api-rest/openapi/openapi_content_data.json post /contents/v1/tags Creates a custom tag in your organization. Use the returned `id` when assigning tags to a document via **PATCH** `/contents/v1/documents/{content_id}` (pass tag IDs in the `tags` array, not names). Tag names supplied at upload time via **POST** `/contents/v1/documents` are resolved by name; for post-upload changes, use tag IDs from this endpoint or from List tags. # Delete tag Source: https://docs.bigdata.com/api-reference/tags/delete-tag /api-rest/openapi/openapi_content_data.json delete /contents/v1/tags/{tag_id} Deletes a custom tag by ID. Any documents linked with this tag will have the association removed. # List tags Source: https://docs.bigdata.com/api-reference/tags/list-tags /api-rest/openapi/openapi_content_data.json get /contents/v1/tags Returns all tags visible to the user's organization, with the number of documents associated with each tag. Use the optional `prefix` query parameter to return only tags whose names start with that string (for example `broker:`, `label:`,`from:`, or `to:`). Use the optional `contains` query parameter to return only tags whose names contain that string (for example `My connector`, `My tag` or `my@email.com`). Tags are created automatically for connectors: `label:Connector Name` for any connector type, `from:user@email.com` / `to:user@email.com` for email and `broker:Broker Name` for investment research connectors. # Find by details Source: https://docs.bigdata.com/api-reference/topics/find-by-details /api-rest/openapi/openapi_knowledge_graph.json post /v1/knowledge-graph/topics Find topics from the Bigdata.com event taxonomy. Search by name or description and narrow the results by topic, group, type or subtype. Use the returned `id` in a Topic query filter. # Delete Execution Source: https://docs.bigdata.com/api-reference/workflow-executions/delete-execution /api-rest/openapi/openapi_workflows.json delete /v1/workflow/executions/{execution_id} Permanently delete a stored workflow execution and its result. Use this to manage how long your runs are kept. Deleting a run that is still in progress stops it first. There is no undo. # Get Execution Source: https://docs.bigdata.com/api-reference/workflow-executions/get-execution /api-rest/openapi/openapi_workflows.json get /v1/workflow/executions/{execution_id} Retrieve a stored workflow execution by ID, including its status, resource consumption, and the full result stream replayed in order. This is how you read a run's result after the streaming connection has closed. # List Executions Source: https://docs.bigdata.com/api-reference/workflow-executions/list-executions /api-rest/openapi/openapi_workflows.json get /v1/workflow/executions List stored workflow executions owned by the authenticated user, newest first. Every run submitted to the asynchronous endpoint is stored; a run streamed from `POST /v1/workflow/execute` is stored only if it was executed with `persistence_mode=enabled`. # Clone Template Source: https://docs.bigdata.com/api-reference/workflow-templates/clone-template /api-rest/openapi/openapi_workflows.json post /v1/workflow/templates/{template_id}/clone Create a copy of an existing template with optional field overrides. # Create Template Source: https://docs.bigdata.com/api-reference/workflow-templates/create-template /api-rest/openapi/openapi_workflows.json post /v1/workflow/templates Create a new workflow template. # Delete Template Source: https://docs.bigdata.com/api-reference/workflow-templates/delete-template /api-rest/openapi/openapi_workflows.json delete /v1/workflow/templates/{template_id} Permanently delete a workflow template. # Get Template Source: https://docs.bigdata.com/api-reference/workflow-templates/get-template /api-rest/openapi/openapi_workflows.json get /v1/workflow/templates/{template_id} Retrieve a specific workflow template by ID. # List Community Templates Source: https://docs.bigdata.com/api-reference/workflow-templates/list-community-templates /api-rest/openapi/openapi_workflows.json get /v1/workflow/templates/community List publicly available community workflow templates. # List Templates Source: https://docs.bigdata.com/api-reference/workflow-templates/list-templates /api-rest/openapi/openapi_workflows.json get /v1/workflow/templates List all workflow templates owned by the authenticated user. # Update Template Source: https://docs.bigdata.com/api-reference/workflow-templates/update-template /api-rest/openapi/openapi_workflows.json put /v1/workflow/templates/{template_id} Update an existing workflow template. Only provided fields are modified. # Cancel Workflow Source: https://docs.bigdata.com/api-reference/workflows/cancel-workflow /api-rest/openapi/openapi_workflows.json post /v1/workflow/execute/async/{execution_id}/cancel Stop a running workflow. The response reports the run's status once the cancellation was applied, so no follow-up poll is needed. Cancelling a run twice is harmless. A cancelled run keeps whatever it produced and can be continued later by submitting its `execution_id`. # Execute Workflow Source: https://docs.bigdata.com/api-reference/workflows/execute-workflow /api-rest/openapi/openapi_workflows.json post /v1/workflow/execute Execute a workflow with an inline template definition or a stored template ID. Returns a streaming response via Server-Sent Events. # Stream Workflow Events Source: https://docs.bigdata.com/api-reference/workflows/stream-workflow-events /api-rest/openapi/openapi_workflows.json get /v1/workflow/execute/async/{execution_id}/stream Attach to a submitted run and receive its events live over Server-Sent Events. Optional: the run proceeds whether or not anything is attached, and disconnecting never stops it. Every event carries an `id`. If the connection drops, reconnect to the same URL sending the last id you received in the `Last-Event-ID` header and delivery continues from there. A standard `EventSource` client does this automatically. # Submit Workflow Source: https://docs.bigdata.com/api-reference/workflows/submit-workflow /api-rest/openapi/openapi_workflows.json post /v1/workflow/execute/async Submit a workflow that runs independently of your connection, and return immediately with its `execution_id`. Use this endpoint for production integrations: the run is unaffected if your client disconnects, and its result is always stored. Poll `GET /v1/workflow/executions/{execution_id}` for status and the result, or attach to the event stream for live progress. To continue a run that stopped before it finished, pass its `execution_id`. # Authentication Source: https://docs.bigdata.com/api-rest/authentication To authenticate with the Bigdata.com API, you need to use an API key. You can create and manage your API Keys in the [Developer Platform > API Keys](https://platform.bigdata.com/api-keys) Developer Platform > API Keys The API key must be included in all API requests to the server in a `x-api-key` header. Here is an example of how you can make an authenticated request using `curl`: ```bash theme={null} curl --request POST \ --url https://api.bigdata.com/v1/search \ --header 'Content-Type: application/json' \ --header 'X-API-KEY: ' \ --data '{ "query": { "text": "Microsoft earnings call highlights" } }' ``` We recommend using environment variables to specify your API Key. # Company news coverage Source: https://docs.bigdata.com/api-rest/best-practices/company_news_coverage If you want to analyse upfront how much news coverage your universe of companies receives under your current data packages, reviewing the volume of documents available over the last **month**, **6 months**, and **12 months** helps you decide whether those packages are the right fit for your portfolio, and informs how you design queries in the Search Service to extract the most relevant insights. You can review your current data packages, and explore others that you can unlock, in the [Bigdata Store](https://platform.bigdata.com/store). The script below leverages the [Volume endpoint](/api-reference/search/search-volume), which returns the unique number of documents and unique number of chunks matching a query over a given period. It sets an Entity filter and issues one call per company for the defined window. ## Coverage analysis The script takes as input the file of RavenPack IDs produced by the [Resolve companies](/api-rest/best-practices/resolve_companies) script, so make sure you have resolved your universe before running it. Clone the public repository and follow the instructions in its `README.md` to run the script. Ready-to-run scripts that measure news coverage across your universe of companies over the last month, 6 months, and 12 months. The output file is in CSV format, and you can import it into an Excel by opening a new document, clicking on Data, and selecting "From Text/CSV". How to import CSV in Excel This is an example that only shows the columns of distinct documents in the last month, 6 months and 12 months. Company news coverage example # Resolve companies Source: https://docs.bigdata.com/api-rest/best-practices/resolve_companies Financial analysts need to surface the news and documents that carry real insight about a universe of securities, without the noise of unrelated mentions. To make that possible, RavenPack has built and maintains a Knowledge Graph of more than 7 million companies worldwide, and identifies these entities in every piece of structured data it processes so you can pinpoint relevant content with precision. The first step in any financial workflow built on Bigdata is therefore to **resolve your universe of securities into RavenPack IDs**. Once you have those IDs, you can use them as filters across any of the Bigdata services to unlock the following value: ✅ **Continuity**: Retrieve all the data linked to a company even after it changes its name or ticker, so your history stays complete.
✅ **Precision**: Get only the content where the company was actually detected, avoiding the noise of similar names that refer to something unrelated.
## Resolving your universe The recommended endpoint depends on the type of entity you want to resolve. Use the tabs below to find the right approach for each one. The most reliable way to resolve public companies is through a market identifier: an **ISIN**, **CUSIP**, **SEDOL**, or listing (in `MIC:Ticker` form). Bigdata exposes a dedicated `get` endpoint for each of these, and every endpoint accepts up to **500 identifiers in a single request**, so even large universes can be resolved with very few API calls. | Identifier | Endpoint | | :--------------------- | :--------------------------------------------------------------------------------- | | ISIN | [`/v1/knowledge-graph/companies/isin`](/api-reference/companies/get-by-isin) | | CUSIP | [`/v1/knowledge-graph/companies/cusip`](/api-reference/companies/get-by-cusip) | | SEDOL | [`/v1/knowledge-graph/companies/sedol`](/api-reference/companies/get-by-sedol) | | Listing (`MIC:Ticker`) | [`/v1/knowledge-graph/companies/listing`](/api-reference/companies/get-by-listing) | Private companies don't have market identifiers, so the most reliable way to resolve them is by their **official website**, or by a combination of **name and country**. The [`/v1/knowledge-graph/companies`](/api-reference/companies/find-by-details) endpoint accepts either signal and returns the **top 20 candidate matches** ranked by relevance. In most cases the first result is the company you were looking for. This endpoint resolves a single company per request, so to process a universe of private companies you need to send multiple queries in parallel. The reference scripts below show how to do this with multi-threading while staying within Bigdata rate limits. RavenPack IDs are stable and do not change over time. We recommend persisting them in a database within your platform so you only need to resolve your universe once. ## Try it yourself Ready-to-run scripts that resolve both public and private companies optimally, using multi-threading while respecting Bigdata rate limits. # Domains to whitelist Source: https://docs.bigdata.com/api-rest/bigdata_domains If your company uses a firewall, you must whitelist the following domains to ensure full access to both Bigdata App and API Services: The table below summarizes the protocol, domain, port, and a brief description for each: | Protocol | Domain | Port | Description | | -------- | ---------------------------------------------------------- | ---- | -------------------------------------- | | HTTPS | bigdata.com | 443 | Product website | | HTTPS | [www.bigdata.com](http://www.bigdata.com) | 443 | Product website alias | | HTTPS | app.bigdata.com | 443 | Bigdata Web application | | HTTPS | api.bigdata.com | 443 | API Services | | HTTPS | clerk.bigdata.com | 443 | Authentication and user management | | HTTPS | [https://s3.amazonaws.com](https://s3.amazonaws.com) | 443 | File storage and downloads (Amazon S3) | | HTTPS | [https://upload.bigdata.com/](https://upload.bigdata.com/) | 443 | File uploads to Bigdata platform | | HTTPS | platform.bigdata.com | 443 | Developer Platform | | HTTPS | agents.bigdata.com | 443 | Research Agent Service | | HTTPS | mcp.bigdata.com | 443 | Bigdata Remote MCP tools | Whitelisting these domains allows uninterrupted connectivity for authentication, data access, file uploads, and other essential features of the Bigdata platform. # Introduction Source: https://docs.bigdata.com/api-rest/content_introduction ## Overview The **Bigdata Content API** lets you manage and query private content that you or your organization uploads to Bigdata. After enrichment, documents are indexed by default so they are available for the Search and Research Agent. You can skip indexing or long-term storage on direct upload with `no_index` and `no_store`. You can onboard content in two ways: * **Connectors API**: For asynchronous, unsupervised, or automated workflows where content is not directly accessible by the user (e.g. email inbox, broker investment research feeds, SharePoint). You configure a connector and the service ingests the content from that source. * **Direct upload (POST /documents)**: For clients that manage their own corpus and want to build the ingestion workflow manually. You request a pre-signed URL and document id; you upload each file via PUT to that URL, then use the id to poll for enrichment status. The workflow uploads your document and enriches it (extraction, structure and annotation of the content). By default it also indexes the document for Search and Research Agent. Optional **`no_index`** and **`no_store`** flags skip indexing or retain the file for only 24 hours. See [Processing options](#processing-options). Both paths produce **documents** that you can list, tag, filter, and use with the Search and Research Agent Services. You can create and manage **Connectors** in the [Developer Platform > Connectors](https://platform.bigdata.com/connectors) (**Bigdata Connectors Management**). Use that guided flow to set up connectors in **four simple steps**. Developer Platform > Connectors *** ## Connectors **Connectors** are for ingestion that is asynchronous, unsupervised, or part of a workflow where content is not directly in the user’s hands, for example, an email inbox, a broker **investment research** feed, or a SharePoint library. * You **create a connector** with a type, label, and type-specific configuration. Supported types include **Email Inbox**, **Investment research**, and **Microsoft SharePoint**. * For **Email**, the API returns an inbox address; you forward messages from allowed senders to that address. Set up automatic forwarding rules in your email client to start building your corpus, Bigdata will ingest and process content automatically. * For **Investment research**, provide broker credentials when you [create the connector](/api-reference/connectors/create-connector). Bigdata then **syncs research documents** from the broker for you. You can [retrigger a sync](/api-reference/connectors/trigger-connector-sync) with a `date_limit` when you need to refresh from a given date. Ingested documents are [tagged](/api-reference/tags/list-tags) with the broker name and **classified using Bigdata’s document taxonomy**, so you can filter and search them consistently alongside the rest of Bigdata corpus. * For **Microsoft SharePoint**, use the same create endpoint with `"type": "sharepoint"` and **`config`** containing only **`session_id`**: a token for the session authenticated via OAuth. For how to obtain **`session_id`**, contact [support@bigdata.com](mailto:support@bigdata.com). As an alternative, follow the steps in [Bigdata Connectors Management](https://platform.bigdata.com/connectors). * Content arriving through the connector is turned into **documents** you can manage and use via Search and Research Agent Services. * Optionally set **`enrichments`** when you [create the connector](/api-reference/connectors/create-connector) to configure the processing pipeline to apply extra enrichment steps to every document ingested through it. See [Enrichments](#enrichments). Typical operations: * **[Create connector](/api-reference/connectors/create-connector)**: Register a new ingestion source. We recommend using [Bigdata Connectors Management](https://platform.bigdata.com/connectors) for a simple guided setup. * **[List connectors](/api-reference/connectors/list-connectors)**: List all connectors you can access; use connector IDs to filter documents or to update, delete, or call sync. * **[Get connector](/api-reference/connectors/get-connector-by-id)**: Fetch full details for one connector (config, share settings, timestamps). * **[Update connector](/api-reference/connectors/update-connector-by-id)**: Change label, description, sharing, or **config** when supported. * **[Trigger connector sync](/api-reference/connectors/trigger-connector-sync)**: Queue another synchronization for an **investment\_research** connector (POST with `date_limit` `YYYY-MM-DD` to resync from that date onward) or a **sharepoint** connector (POST with an empty body `{}`). * **[Delete connector](/api-reference/connectors/delete-connector-by-id)**: Soft-delete (archive) a connector by default—it stops ingesting new content but existing documents remain. Use `?force_delete=true` to trigger a hard delete: all files related to the connector are deleted asynchronously, then the connector is removed from the database. Once a connector is set up, documents are ingested according to its configuration. *** ## Documents **Documents** are the items Bigdata has uploaded and enriched, whether they came from a connector (e.g. email, SharePoint) or from **direct upload**. By default they are also indexed for search and analysis. **Direct upload** is intended for clients that manage their corpus and want to build the ingestion workflow from scratch: you choose what to send, when, and with what metadata (file name, tags, sharing, enrichments, processing options). The main focus is **enrichment**: once you upload the file (PUT to the pre-signed URL), Bigdata enriches it (extraction, structure and annotation of the content). By default it then indexes the document for Search and Research Agent. Optionally set **`enrichments`** when you [are uploading the file](/api-reference/documents/enrich-document) to configure extra pipeline steps. See [Enrichments](#enrichments). Optionally set **`no_index`** or **`no_store`** to skip indexing or long-term retention. See [Processing options](#processing-options). Once you get the pre-signed URL and document id; PUT the file to that URL, then use the id with [Get document metadata](/api-reference/documents/get-document-metadata) to poll for status until processing is complete. The following operations apply to all documents, whether they were ingested via a connector or direct upload: * **[List documents](/api-reference/documents/list-documents)**: Paginated list of documents you can access. Supports filtering and sorting (including `origin` values `email`, `investment_research`, `sharepoint`, and `file_upload`); each item includes a content ID for use with the other document endpoints. * **[Get document metadata](/api-reference/documents/get-document-metadata)**: Return metadata for one document by content ID (status, file name, connector, tags, enrichments, usage, timestamps). Use this to check processing status before downloading content. * **[Update document metadata](/api-reference/documents/update-document-metadata)**: Change which tags are assigned to a document and whether the document is shared with your organization. * **[Get annotated document](/api-reference/documents/get-annotated-document)**: Return a time-limited pre-signed URL. GET that URL to download **private** document content as structured JSON (metadata, title, body blocks, entities, sentences with sentiment). Use for search indexing, entity extraction, or structured display. * **[Get original document](/api-reference/documents/get-original-document)**: Return a time-limited pre-signed URL. GET that URL to download the **private** document’s original file in its native format (e.g. .eml, .pdf). * **[Delete document](/api-reference/documents/delete-document)**: Remove a document from the platform. Deletes the original document, annotated version, and chunks from the vector database. Documents can be **tagged** automatically from ingestion, for example **sender/recipient-metadata** tags for email, and **`broker:Broker Name`** for investment research. You can also define **custom tags** and attach them to documents after upload. *** ## Tags Tags help you organize and filter documents in **Search Service** and **Research Agent**. * **[List tags](/api-reference/tags/list-tags)**: List tags visible to your organization (including connector-generated tags), with document counts. Use optional `prefix` to narrow results (for example `broker:`, `from:`, or `to:`). * **[Create tag](/api-reference/tags/create-tag)**: Create a custom tag by name. The response includes an `id` you use when updating document metadata. * **[Delete tag](/api-reference/tags/delete-tag)**: Deletes a custom tag by ID. Any documents linked with this tag will have the association removed. To change tags on an existing document, call **[Update document metadata](/api-reference/documents/update-document-metadata)** with a `tags` array of **tag IDs** (not names). The array replaces the document's current tags, so you can extend or reduce the set by sending the full list you want. Every ID must exist; otherwise the API returns `400` with `INVALID_TAGS_ERROR`. You can combine tag updates with `share_with_org` in the same request to change organization-wide visibility. *** ## Enrichments **Enrichments** configure the processing pipeline to apply additional steps to your content. You can set them per document on [direct upload](/api-reference/documents/enrich-document) or per connector on [Create connector](/api-reference/connectors/create-connector) (applied to every document ingested through that connector). Pass an **`enrichments`** array of enrichment names in the request body. | Enrichment | Description | | -------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `reporting_entities` | Identifies the document's **reporting company**, using the same concept as the [`ReportingEntity` reporting detail](/getting-started/search/query_filters#reporting-details) in Search. This keeps the reporting entity consistent with the rest of the Bigdata corpus, so you can reliably filter private content, transcripts and filings together. | | `translation` | Translates the document content so non-English material can be searched and analyzed alongside the rest of your corpus. Supports more than 70 languages. | You can request one or more enrichments in the same request: ```json theme={null} { "file_name": "Q2_2025_equity_research_note.pdf", "published_ts": "2025-06-15T10:30:00Z", "tags": ["equity-research", "sector:semiconductors"], "share_with_org": false, "enrichments": ["reporting_entities", "translation"] } ``` After processing, document metadata from [List documents](/api-reference/documents/list-documents) and [Get document metadata](/api-reference/documents/get-document-metadata) exposes: * **`enrichments_requested`**: The enrichments you asked for (on upload or via the connector). * **`enrichments_applied`**: The enrichments that completed successfully. Compare the two arrays to see what is still pending or was not applied. *** ## Processing options On [direct upload](/api-reference/documents/enrich-document), two optional boolean flags control whether the document is indexed and how long it is retained. Both default to omitted/`false` (enrich, store, and index). | Flag | Effect | | ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `no_index` | Enrich the document but **do not index** it. Original and annotated files remain stored and retrievable via the Content API. The document is **not** available in Search or Research Agent. | | `no_store` | Enrich the document, **do not index** it, and keep it retrievable for **24 hours after enrichment completes**. After that the document is deleted. Use this for single-use processing. | You can set both flags to `true`. `no_store` already skips indexing, so `no_index` has no additional effect in that case. These flags apply only to **direct upload** (`POST /contents/v1/documents`). Connector-ingested documents are still stored and indexed. *** ## Typical flow **Using connectors (async / unsupervised):** 1. **[Create a connector](/api-reference/connectors/create-connector)** (e.g. email) with type, label, and config; for email, use the returned inbox address to forward messages. 2. Optionally check that content has been enriched and indexed by [listing your recent documents](/api-reference/documents/list-documents). 3. Use your content in the Search or Research Agent Service (e.g. filter by **Emails** in the playgrounds below). **Using direct upload (manual corpus):** 1. Call **[Enrich document](/api-reference/documents/enrich-document)** with metadata (file name, tags, sharing, and optional `no_index` / `no_store`); use the returned URL to PUT the file (upload it). 2. Poll [Get document metadata](/api-reference/documents/get-document-metadata) with the returned id to check `status` until processing is complete (`completed`). See [Get document metadata](/api-reference/documents/get-document-metadata) in the API reference. If you set `no_store`, download the annotated or original file within 24 hours of completion. 3. Use indexed content in the Search or Research Agent Service (e.g. filter by **My Files** in the playgrounds below). Documents uploaded with `no_index` or `no_store` are not searchable. Search across your private content and other sources. In the playground, open the source selector and choose **My Files** to limit results to your uploaded documents. Run research over your private content and real-time data. In the playground, use the source selector and filter by **My Files** to ground answers in your documents. *** ## Authentication and reference All endpoints require an API key sent in the `X-API-KEY` header. See [Authentication](/api-rest/introduction) for details. Use the **API reference** (endpoints listed in this section) for request/response schemas, parameters, and examples. You can try the API from the [Developer Platform](https://platform.bigdata.com) playgrounds. # Introduction to Bigdata APIs Source: https://docs.bigdata.com/api-rest/introduction Bigdata APIs let your proprietary platform access Bigdata services in a deterministic, programmable way. If you prefer to build workflows orchestrated by AI agents, you can reach the same services through the [MCP server](/mcp-reference/introduction) or the [Bigdata CLI](/cli-reference/introduction). This page is the reference for every available Bigdata endpoint and the authoritative source for all supported parameters. You can try requests directly from the playgrounds linked below, or, for a simpler and more user-friendly experience, run them from the [Developer Platform](https://platform.bigdata.com). Search for entities using Bigdata's knowledge graph tools. Easily find the most relevant information from trusted sources and your own data. Use it to power agents that give accurate, real-time answers. Monitors API Coming soon} icon="radar" href="/getting-started/monitors/overview"> Save a search, run it continuously, and extract grounded, structured events from newly matched content. Get faster insights and smarter decisions using our advanced AI capabilities and real-time data. Build reproducible, templated research workflows for automated analysis. Upload and manage your own private or proprietary content so it can be searched and analyzed alongside Bigdata's corpus. Access comprehensive financial data including corporate events, intraday prices, analyst ratings, estimates, and earnings surprises. ## Pricing and usage monitoring See the [Bigdata API pricing page](/getting-started/bigdata_api_pricing) for full details on plans and metering. You can monitor consumption programmatically through the [subscriptions endpoint](/api-reference/quotas/get-subscription-quotas), as described in the [Monitor usage how-to guide](/how-to-guides/monitor_usage), or visually from the [Developer Platform](https://platform.bigdata.com/usage). # Bigdata Developer Platform We recommend using the [Developer Platform](https://platform.bigdata.com) to test your queries and understand how our APIs work. Also, use it to manage your API keys and monitor your API consumption and costs. **Your companion for day-to-day Bigdata API development** The Developer Platform is your central hub for managing, testing, and optimizing your Bigdata API integrations. Get instant business value with interactive playgrounds that make it incredibly easy to understand how our APIs work and discover their full potential. **Key Features:** * **🎮 Advanced Playgrounds**: Interactive environments with visual input/output to experiment with queries and see results instantly * **🔑 API Management**: Centralized control of your API keys and access credentials * **📊 Usage & Spending Tracking**: Monitor your API consumption and costs in real-time * **📱 Demo Apps Library**: Explore pre-built applications showcasing what's possible with Bigdata APIs # Workflows API Source: https://docs.bigdata.com/api-rest/workflows/introduction Build reproducible, templated research workflows for automated analysis The **Workflows API** enables templated, reproducible research designed for automation. Unlike the conversational Research Agent, Workflows uses parameterized templates that produce consistent outputs across executions. ## Workflows vs Research Agent | Feature | Research Agent | Workflows API | | --------------------- | ------------------------------- | --------------------------------- | | **Interaction style** | Ad-hoc natural language queries | Templated, reproducible research | | **Execution** | Single execution | Reusable templates | | **State management** | Conversational (chatId) | Parameterized (template + inputs) | | **Best for** | Exploration and discovery | Automation and production | | **Research plan** | Dynamic, agent-determined | Optional predefined steps | ## Core Concepts ### Templates Templates are reusable research specifications that define: * **Prompt**: The research question with Jinja2 placeholders (e.g., `{{ company_id }}`) * **Expected inputs**: Typed parameters the template requires * **Content filters**: Optional restrictions on which sources to search * **Research plan**: Optional predefined steps for structured execution * **Expected output**: Optional report template describing the final answer's structure, tone, and format ### Research Plan Behavior The Workflows API behavior is controlled by the presence of a `research_plan`: * **Without a plan**: The agent dynamically determines research steps based on your prompt. * **With a plan**: The agent follows your predefined steps for structured, predictable output. ### Input Types Templates support two input types: * `rp_entity_id`: A Bigdata entity ID (e.g., company identifier like `D8442A`) * `string`: Free-form text input ## Quick Links Get started with your first workflow execution Submit a run that outlives your connection, then read, watch, or cancel it Learn how to build effective templates Learn how research plans affect execution Discover and clone shared templates ## Running a workflow: synchronous or asynchronous A workflow can stream its result on the connection that started it, or run independently of that connection. * **`POST /v1/workflow/execute`** streams the whole run back on the same HTTP response. Closing the connection cancels the run. * **`POST /v1/workflow/execute/async`** returns an `execution_id` immediately and the run continues on its own. Its result is always stored, you can attach to its event stream at any point, and disconnecting never stops it. Use the asynchronous endpoint for production integrations. See [Running a workflow](/how-to-guides/agents/workflows/running-a-workflow). ## API Endpoints The Workflows API provides the following endpoints: | Endpoint | Method | Description | | -------------------------------------------------- | ------ | --------------------------------------------------------------- | | `/v1/workflow/execute` | POST | Execute a workflow and stream the result on the same connection | | `/v1/workflow/execute/async` | POST | Submit a workflow that runs independently of your connection | | `/v1/workflow/execute/async/{execution_id}/stream` | GET | Attach to a submitted run and receive its events live | | `/v1/workflow/execute/async/{execution_id}/cancel` | POST | Stop a running workflow | | `/v1/workflow/executions` | GET | List your stored runs | | `/v1/workflow/executions/{execution_id}` | GET | Retrieve a stored run with its full result | | `/v1/workflow/executions/{execution_id}` | DELETE | Delete a stored run | | `/v1/workflow/templates` | GET | List your templates | | `/v1/workflow/templates` | POST | Create a new template | | `/v1/workflow/templates/{id}` | GET | Get a specific template | | `/v1/workflow/templates/{id}` | PUT | Update a template | | `/v1/workflow/templates/{id}` | DELETE | Delete a template | | `/v1/workflow/templates/community` | GET | Browse community templates | | `/v1/workflow/templates/{id}/clone` | POST | Clone a template to your account | ## Available Models Select the model that best fits your use case: | Model | Description | | ------ | ----------------------------------- | | `base` | Default model, balanced performance | | `pro` | Enhanced reasoning capabilities | ## Time Range Options Control the time range of research data: **Rolling time ranges:** * `last_24_hours` * `last_7_days` * `last_30_days` * `last_60_days` * `last_90_days` * `last_180_days` * `last_365_days` **Custom date range:** ```json theme={null} { "start": "2024-01-01T00:00:00Z", "end": "2024-12-31T23:59:59Z" } ``` ## Streaming Response The Workflows API returns responses via Server-Sent Events (SSE). Each event wraps a typed payload in a `delta` field. The most common message types: | Type | Description | | ----------- | -------------------------------------------- | | `THINKING` | Agent's reasoning process | | `PLANNING` | Research plan with steps | | `ACTION` | Tool being called | | `ANSWER` | Final response content | | `GROUNDING` | Source references | | `AUDIT` | Search results and traces | | `COMPLETE` | Execution finished with resource consumption | | `ERROR` | Error occurred | This list is abbreviated. For every public message type -- including `LLM_RETRY`, `TOOL_ERROR`, and `STRUCTURED_OUTPUT` -- their field schemas, when each fires, and a copy-paste Python handler, see [Streaming responses](/how-to-guides/agents/concepts/streaming-responses). # Chatting with your files Source: https://docs.bigdata.com/app/getting-started/chat_with_your_files Bigdata lets you upload and interact with your own files. This is available on both desktop and mobile. Need to analyze a specific report, contract, or research paper? Simply upload it, and Bigdata will help you extract the key information you need. It's a powerful tool that saves you time and ensures you get the most out of your research. There are two ways to chat with your documents: ## Chat with Files from the homepage * Click the paperclip icon to attach one or more files. * Type your question or request. * Hit "Send" and Bigdata will analyze your uploaded documents. **Good to know:** If you upload a document without a question, Bigdata will automatically "Summarize this document" to get you started. ## Using the "My Files" page * Drag and drop your files onto the page for easy upload (Desktop Only) * Alternatively, select files using the checkboxes. * Click the chat icon (appears next to the 3-dot menu) to initiate a chat. * Type your question and Bigdata will get to work. # How Bigdata generates your answers Source: https://docs.bigdata.com/app/getting-started/how_generates_answers ## Introducing the Audit Trail When you ask a question, Bigdata breaks it down into smaller, more focused queries. These queries are then sent to various finance-focused language models for a comprehensive response. To understand Bigdata's reasoning, look for the "Show Audit Trail" icon at the bottom of each Bigdata chat response. It provides a step-by-step breakdown of how your answer was generated. Clicking the icon reveals the step-by-step process Bigdata uses to build your answer: * **Understanding your question:** Bigdata first analyzes your prompt to grasp its meaning and intent. * **Formulating queries:** based on your question, Bigdata generates specific queries to retrieve relevant information. * **Revealing information sources:** for each query, Bigdata identifies the exact sources it uses to gather the information, for more transparent and trustworthy insights. # Bigdata Assistant Source: https://docs.bigdata.com/app/introduction The [Bigdata Assistant](https://bigdata.com) is a next-generation AI tool tailored for professionals navigating fast-moving financial environments. Purpose-built to support real-time decision-making, it streamlines search and discovery across a wide range of information sources — including proprietary databases, public filings, premium financial content, and gated research, and structured data sources. Now you can automate routine analysis with pre-built Workflows, monitor your portfolio with an interactive Watchlist, precisely select your sources with the Content Catalogue, and tackle complex questions with our Research agent. By understanding context and intent, the Assistant surfaces both relevant and trustworthy insights instantly, helping users cut through information overload and act with confidence. ## Why use the Bigdata Assistant? Finance professionals are often hesitant to use conversational chatbots due to several unmet needs: * **Transparency of sources** * Every insight is fully attributable, showing you the exact source of the information. * You can also take control by using the Content Catalogue to filter and select from specific trusted sources before asking a question. * **Real-time accuracy** * Our agent is grounded in real-time data, ensuring you get insights that are accurate up to the very last minute and reducing the risk of outdated information. * **Specialized Depth** * Generic chatbots provide superficial answers. For complex questions, our Deep Research agent plans and executes a multi-step analysis, drawing insights from the right datasets—structured and unstructured alike—to deliver the nuanced, expert-level information that professionals rely on. ## How Bigdata.com reinvents business search Bigdata combines finance-specific language models with our proprietary Knowledge Graph, which connects vast amounts of structured and unstructured financial data. This data comes from trusted sources, with full traceability and auditability on every answer: * **Public sources:** over 13,500 financially relevant web content sources, including SEC regulatory filings. * **Transcripts for 40,000 listed companies** including earnings results, analyst briefings, and company conferences. * **Gated sources:** premium insights from RavenPack, FactSet, MT Newswires, Benzinga, The Fly, Alliance News, FXStreet, LinkUp. * **Internal sources:** company data from file servers, eComms, CRM, ERP, BI Tools. ### Real-time knowledge, fewer hallucinations Our agent is grounded in real-time data, which helps build trust and produce timely, accurate insights. ## How Bigdata empowers financial workflows Use the Assistant to gain market intelligence, automate research, and make informed financial decisions. * **Ask complex questions:** Use natural language to have the Deep Research agent plan and execute multi-step research. * **Launch pre-built Workflows:** Automate routine analysis, like preparing a detailed earnings preview, in just a few steps. * **Create briefs and reports:** Instantly generate summaries and reports from high-quality data sources with full attribution. * **Upload your own content:** Chat with your files to quickly find key information, generate summaries, or ask specific questions about the documents. * **Monitor your portfolio:** Use the Watchlist to monitor your portfolio, create custom lists, or track curated indices. ## Why Financial users choose Bigdata App and API * **Enterprise-Grade Security:** Your data is kept completely private, is never used for model training, and is protected by ISO 27001 compliance, with SOC 2 certification expected by the end of the year. * **Smarter Than Chatbots:** Purpose-built for the financial industry, our proprietary Knowledge Graph understands complex financial relationships, delivering more precise and attributable results than generic AI. * **One-Stop Shop:** Create a single source of truth by securely uploading proprietary documents to be searched alongside premium financial data and public content, all within one easy-to-use platform. * **Workflow Automation:** Go beyond simple Q\&A by using pre-built workflows to automate complex, routine analysis like earnings previews, saving valuable time and reducing manual effort. # Building investment cases Source: https://docs.bigdata.com/app/use-cases/equity-research/building_investment_cases To build a compelling investment case is a complex, time-consuming process that can take weeks. That is because it requires a thorough analysis of financial data, market trends, risks and opportunities. Yet most of this information is scattered across the internet, sometimes behind paywalls. Bigdata streamlines this process. It provides efficient, real-time access to reliable sources, such as transcripts, news, fillings and market reports. In this example, we use Bigdata to help us build an investment case for Anthropic from scratch. Let's start with a general question: > How does Anthropic stand as a potential investment opportunity? Based on the information I have, Anthropic is a leading artificial intelligence (AI) company that has raised significant funding from major tech companies such as Amazon and Google. The company was founded by former employees of OpenAI and has since become a formidable competitor in the AI space. Anthropic has differentiated itself from OpenAI by structuring itself as a public benefit corporation, meaning its board is legally empowered to balance returns for investors with a separate mission to ensure that "transformative AI helps people and society flourish." This focus on safety and responsibility has attracted business customers from various industries, including drug maker Pfizer and conversational search engine Perplexity AI. The company has also developed a chatbot named Claude, which it has made available as an iPhone app. According to reports, Anthropic projects will take in more than \$850 million in annualized revenue by the end of 2024. This revenue growth is driven in part by the increasing demand for AI technology in various industries. Anthropic has also received funding from other investors, including Google, which invested about \$300 million in the company in late 2022. The company has also sold its shares to other investors, including ATIC Third International Investment Company LLC, associated with the UAE's sovereign wealth fund Mubadala, which acquired nearly \$500 million worth of FTX's Anthropic shares. These investments provide a strong foundation for Anthropic's growth and development. Furthermore, Anthropic's focus on safety and responsibility sets it apart from other AI companies and positions it well to address the potential risks associated with transformative AI. This focus on safety and responsibility is likely to be a winning strategy in the long run, as it aligns with the growing concern among investors and the public about the ethical implications of AI technology. In conclusion, Anthropic is a well-funded and rapidly growing AI company with a strong focus on safety and responsibility. Its differentiated business model, attractive customer base, and strong financial position make it an attractive investment opportunity for those looking to capitalize on the emerging AI market. ## Projected Growth Trajectory With that big picture in mind, let's ask Bigdata to provide a more data-driven forecast of Anthropic's future growth potential. > What is the projected growth trajectory for Anthropic's revenue and market share in the next 5 years? Anthropic is projected to take in more than \$850 million in annualized revenue by the end of 2024. The company's financial needs may continue to grow in the coming years as the cost of training models is expected to reach \$100 billion. Anthropic's focus on safety and responsibility, as well as its partnerships with major tech companies like Amazon and Google, position it well to address the potential risks associated with transformative AI and attract business customers from various industries. Regarding market share, there is no specific information available in the given news snippets to make a definitive projection. However, Anthropic's differentiated business model, attractive customer base, and strong financial position make it a competitive player in the AI market. The increasing demand for AI technology in various industries and Anthropic's focus on safety and responsibility are likely to contribute to its growth in market share. ## Potential Risks and Challenges Bigdata can also help build a comprehensive risk assessment and identify potential regulatory hurdles, competition from other companies, or technical limitations. > Analyze the potential risks and challenges that Anthropic might face in its development and commercialization of AI solutions. One of the most significant risks is the potential misalignment between the objectives of the AI system and human values. Anthropic recognizes this risk and has made it a priority to ensure that its AI systems are aligned with human values. The company has implemented a Responsible Scaling Policy, which pledges not to release AIs above certain capability levels until it can develop sufficiently robust safety measures. This approach aims to pressure competitors to make similar commitments and eventually inspire binding government regulations. Another risk is the possibility of AI systems developing autonomy or falling into the wrong hands. Anthropic recognizes this risk and is investing in research to identify and address these potential issues. The company has made a major breakthrough in this area by identifying millions of "features" inside a version of Claude, which allows researchers to alter the behavior of the system by toggling these features on and off. A third risk is the financial pressure to scale up operations and meet the increasing demand for AI technology. Anthropic has raised significant funding, but it may need to raise even more in the future. The company's structure as a public benefit corporation, which balances returns for investors with a mission to ensure that AI helps people and society flourish, may come under pressure from corporate juggernauts. ## Financial Performance Comparison When building an investment case, it's important to have insights into the company's relative strength and weaknesses within the market. Let's ask Bigdata to compare Anthropic's financial performance to its key competitors. > Compare Anthropic's financial performance and valuation to its key competitors, such as OpenAI and DeepMind. Focus on key metrics like revenue, profitability, and valuation, and consider the current state of the AI market and the specific segments each company is targeting. **Anthropic:** * Has raised a total of \$7.6 billion in funding * Projected to take in more than \$850 million in annualized revenue by the end of 2024 * Received funding from major tech companies like Amazon and Google * Focus on safety and responsibility and partnerships with industry leaders position it well in the market **OpenAI:** * Valued at over \$80 billion to \$90 billion * Generated over \$1.6 billion in revenue in the past year * Expanding its board and seeking funding for a new AI chip venture * Microsoft-backed, making it a significant player in the enterprise AI market **DeepMind:** * No recent financial performance or valuation data available * Has made significant strides in AI research and collaborations with industries and academia * Google-owned, giving it access to significant resources and market reach ## Strategic Partnerships Strategic partnerships can offer investors insights into the company's growth strategies and potential for market expansion. In our case, we ask Bigdata to identify Anthropic's key collaborations such as joint ventures, technology integrations, or access to new markets. > Identify potential strategic partnerships or collaborations that could further enhance Anthropic's growth and market position. Anthropic has already established strategic partnerships with major tech companies like Amazon and Google, which have provided it with significant funding, chips, and cloud infrastructure. These partnerships have helped Anthropic maintain independence and differentiate itself from competitors that are more closely tied to one large investor. Additionally, Anthropic has collaborated with AWS and Accenture to help organizations responsibly adopt and scale generative AI technology. This collaboration has enabled Anthropic to provide its AI systems to a wider customer base, especially in highly-regulated industries like healthcare, public sector, banking, and insurance. Another potential collaboration could be with industry associations, research institutions, and government agencies through AI Apex Asia or similar organizations. Such collaborations could provide Anthropic with valuable insights into best practices, emerging trends, and regulatory requirements in the AI market. They could also offer opportunities for joint initiatives and collaborative efforts to address critical challenges and explore frontier advancements in AI. Furthermore, as the open-source world grapples with security and licensing issues for generative AI, Anthropic could collaborate with initiatives like the Linux Foundation and CNCF to develop standards and guidelines for safe and ethical AI use. This collaboration could help Anthropic position itself as a leader in the responsible development and deployment of AI technology, while also contributing to the broader AI ecosystem. ## Writing the investment case As a final step, let's ask Bigdata to puzzle all the findings into a compelling investment case. > Based on the analysis above, construct an investment case for Anthropic, incorporating risk factors to determine its value and assess its investment potential. ### Investment Case for Anthropic #### Overview Anthropic is a rapidly growing artificial intelligence (AI) startup that has secured significant funding from major tech companies like Amazon and Google. The company's focus on safety and responsibility, as well as its partnerships with industry leaders, have positioned it well in the market. In this investment case, we will summarize key findings from the analysis above on Anthropic's growth trajectory, risks, financial performance comparison, and strategic partnerships. We will also provide an assessment of Anthropic's investment potential. #### Growth Trajectory Anthropic's financial performance is projected to be strong, according to available data. The company has raised a total of \$7.6 billion in funding and is projected to take in more than \$850 million in annualized revenue by the end of 2024. Anthropic's revenue growth and valuation are still lower than its competitors OpenAI and DeepMind, but the company's independence from a single large investor and its collaborations with AWS and Accenture provide it with unique advantages. #### Risks There are risks associated with investing in Anthropic. One risk is the rapidly changing nature of the AI market, which could make it difficult for the company to maintain its competitive edge. Another risk is regulatory uncertainty, as governments and industry associations continue to grapple with the ethical and safety implications of AI technology. However, these risks are mitigated by Anthropic's focus on safety and responsibility, its partnerships with major tech companies and industry leaders, and its collaborations with industry associations, research institutions, and government agencies. These collaborations could provide valuable insights into best practices and emerging trends in the AI market. Furthermore, Anthropic's commitment to responsible AI development and deployment could position it well to capitalize on the growing demand for ethical and safe AI technology. #### Financial Performance Comparison Anthropic has raised a total of \$7.6 billion in funding and is projected to take in more than \$850 million in annualized revenue by the end of 2024. OpenAI, on the other hand, is valued at over \$80 billion to \$90 billion and generated over \$1.6 billion in revenue in the past year. DeepMind, which has made significant strides in AI research and collaborations with industries and academia, does not have recent financial performance or valuation data available. While Anthropic's revenue growth and valuation are lower than its competitors, its independence from a single large investor and its collaborations with AWS and Accenture provide it with unique advantages. #### Strategic Partnerships Anthropic has already established strategic partnerships with major tech companies like Amazon and Google, providing it with significant funding, chips, and cloud infrastructure. Additionally, Anthropic's collaborations with industry associations, research institutions, and government agencies could provide valuable insights into best practices and emerging trends in the AI market. Furthermore, Anthropic's focus on responsible AI development and deployment could position it well to capitalize on the growing demand for ethical and safe AI technology. Some potential collaborations could include: * Industry associations: Collaborating with industry associations like AI Apex Asia or similar organizations could provide Anthropic with valuable insights into best practices, emerging trends, and regulatory requirements in the global AI market. * Research institutions: Collaborating with research institutions like MIT, Stanford, or Carnegie Mellon could provide Anthropic with access to cutting-edge research and expertise in AI and related fields. This could help Anthropic stay at the forefront of AI research and development. * Government agencies: Collaborating with government agencies like the National Institute of Standards and Technology (NIST) or the European Union Agency for Cybersecurity (ENISA) could provide Anthropic with valuable insights into regulatory requirements and best practices for responsible AI development and deployment. It could also offer opportunities for joint initiatives and collaborative efforts to address critical challenges and explore frontier advancements in AI. #### Investment Potential Anthropic's strong financial performance, unique advantages in the market, strategic partnerships, and commitment to responsible AI development make it an attractive investment opportunity. While there are risks associated with investing in anthropic, such as the rapidly changing nature of the AI market and regulatory uncertainty, these risks are mitigated by the company's focus on safety and responsibility, its partnerships with major tech companies and industry leaders, and its collaborations with industry associations, research institutions, and government agencies. Furthermore, Anthropic's commitment to responsible AI development and deployment could position it well to capitalize on the growing demand for ethical and safe AI technology. # Tracking Investment Trends Source: https://docs.bigdata.com/app/use-cases/equity-research/tracking_investment_trends ## Get real-time insights for informed decisions Investors constantly seek out industries primed for significant growth and potential disruption. Traditionally, this has been a subjective, time-consuming process. Bigdata analyses information from premium news sources, social media, financial data to help identify industries that experience a surge in demand or technological breakthroughs. This framework demonstrates how Bigdata can be used to assess the investment potential of an industry, using **robotic surgery** as an example. ## Market Analysis Let's start with the essentials for constructing a robust ROI model and ask Bigdata to provide information about the size and growth projections of this new market. > Summarize the market size and growth projections for the global medical robotics and computer-assisted surgery market. The global market for medical robotics and computer-assisted surgery is projected to reach \$19.5 billion by 2028, growing at a compound annual growth rate of 11.0% during the forecast period. This growth is driven by technological advances, increased adoption, rising rates of chronic disease, an aging population, demand from surgeons, and favorable reimbursement policies. ## Key Players With a better grasp of the market potential, let's now identify the key players in this space. We ask Bigdata to provide a comprehensive landscape analysis and help pinpoint companies with the strongest value propositions. > Which specific companies are talking about Robotic Surgery investments? Investments in robotic surgery companies are on the rise. For instance, Fidelity Management & Research Company led a \$110 million investment in MMI, and Intuitive Surgical announced FDA clearance of its fifth-generation robotic system, da Vinci 5. These developments further underscore the focus on robotic surgery and its potential to enhance healthcare infrastructure and contribute to socio-economic development. Nami Surgical is one of the companies that has recently secured investment for robotic surgery. The investment was led by Eos Advisory and included the Investment Fund for Scotland, Maven, Scottish Enterprise, SIS Ventures, and Innovate UK. Other companies mentioned in the news snippets as key players in the medical robotics and computer-assisted surgery market include Intuitive Surgical Operations, Medtronic, Stryker, and Zimmer Biomet. ## Specific Areas of Focus For a more nuanced investment thesis, Bigdata can help narrow down the research to specific applications in Robotic Surgery: > Are there particular areas within robotic surgery (e.g., minimally invasive procedures, specific surgeries) receiving more focus? Based on the information I have, there are several areas within robotic surgery that are receiving significant focus. One such area is minimally invasive procedures, as robotic surgery enhances surgical precision and dexterity, leading to reduced patient trauma, post-operative pain, and recovery times. This results in shorter hospital stays and improved patient outcomes. Another focus area is specific surgeries such as urology, gynaecology, and colorectal procedures. Companies like Nami Surgical are developing pioneering technology to integrate ultrasonic scalpels in robotic surgeries, setting a new benchmark in surgical care. ## Investment Strategies And to further unpack a company's competitive edge and risk profile, Bigdata can offer insights into their strategic playbook, including internal R\&D, strategic acquisition or partnership dynamics. **Tip**: Click on the "Show Audit trail" icon at the bottom of the response to see how Bigdata breaks down your prompt and gathers the information necessary to get you an answer. > Are companies investing in developing their own robotic surgery systems, acquiring existing technology, or partnering with other players? Based on the information I have, companies are engaging in various strategies to advance robotic surgery. Some are investing in developing their own technology, while others are acquiring existing systems or forming strategic partnerships. For instance, Nami Surgical recently secured investment to develop its ultrasonic platform for robotic-assisted surgery. In another instance, SpinEM Robotics and Spineart forged a strategic partnership to revolutionize spinal surgery by combining their respective expertise and technologies. Additionally, Stereotaxis announced the acquisition of Access Point Technologies to amplify its efforts in advancing minimally invasive endovascular intervention through robotics. Moreover, significant funding rounds have been reported in the digital surgery technologies market, indicating a growing interest in investing in this field. Companies like Medical Microinstruments, Fabric, and HealthSnap have raised substantial investments to commercialize their surgical robotics platforms and advance AI capabilities. ## Summarizing Market Research Reports Market research and analyst reports are invaluable for validation, but reading them takes ages. Ask Bigdata to summarize the key insights from these reports. **Tip**: You can ask Bigdata to analyse reports from external sources or from your own documents. > Find 3 recent market research reports (past 6 months) on global robotic surgery. Summarize: market size, growth forecast (CAGR), and key players. Based on the information I have, here are summaries of three recent market research reports on global robotic surgery: "Medical Robotics and Computer-assisted Surgery: The Global Market 2023-2028" (Source: ResearchAndMarkets.com) The global market for medical robotics and computer-assisted surgery is projected to grow from \$11.5 billion in 2023 to \$19.5 billion by the end of 2028, at a compound annual growth rate (CAGR) of 11.0% during the forecast period. Key companies profiled in this report include Intuitive Surgical Operations, Medtronic, Stryker, and Zimmer Biomet. "Surgical Robotics Market to Achieve 15.7% CAGR Amidst Increasing Adoption of Advanced Technologies" (Source: PharmiWeb) The global surgical robotics market was valued at USD 6.2 billion as of 2022 and is projected to reach USD 25.7 billion by 2032, growing at a compound annual growth rate (CAGR) of 15.70% during the forecast period from 2033 to 2032. Key players in this market include Intuitive Surgical, Medtronic, Stryker, Zimmer Biomet, and Smith & Nephew. "Global Robotic Surgery Market Size, Share & Industry Analysis, By Type, Application, End User, and Regional Forecast, 2023-2030" (Source: Fortune Business Insights) The global robotic surgery market was valued at \$8.3 billion in 2022 and is projected to reach \$32.4 billion by 2030, growing at a compound annual growth rate (CAGR) of 18.1% during the forecast period. Key players in this market include Intuitive Surgical, Medtronic, Stryker, and Zimmer Biomet. These reports highlight the significant growth and expansion of the global robotic surgery market, driven by technological advances, increased adoption, and favorable reimbursement policies. The market is projected to reach substantial values by the end of the forecast period, indicating potential for significant returns on investment. Key players in the sector include Intuitive Surgical, Medtronic, Stryker, Zimmer Biomet, and others. ## Media Sentiment Bigdata can also analyze media sentiment around a specific topic, for a more nuanced understanding of the industry's prospects. This will reveal whether the media portrays a particular technology or innovation as a positive investment opportunity or a risky venture. **Tip**: Bigdata feeds your knowledge workflows from real-time indexing of 40,000 financially relevant web content sources at scale and gated sources such as Dow Jones, FactSet transcripts, WSJ, Benzinga, MarketWatch, BARRON'S and more. > Analyze the sentiment of media coverage around Robotic Surgery in the past year. Does the coverage portray robotic surgery as a positive investment opportunity or a risky venture? Media coverage around robotic surgery over the past year has generally portrayed it as a positive investment opportunity. The coverage highlights the significant growth and expansion of the market, driven by technological advances, increased adoption, and favorable reimbursement policies. The market is projected to reach substantial values by the end of the forecast period, indicating potential for significant returns on investment. However, it is important to note that media coverage also acknowledges the challenges and risks associated with robotic surgery, such as the need for advanced training for surgeons, high costs, and regulatory norms. These factors may impact the success and profitability of investments in the sector. ## Generating an email with key findings And finally, ask Bigdata to generate an email to your team with the key insight > Building on the information gathered, generate a concise email summarizing the key insights on robotic surgery investment trends. Include findings from media coverage analysis, company investment activities, and market research reports. Subject: Key Insights on Robotic Surgery Investment Trends Dear \[Recipient], I am pleased to provide you with a summary of the latest developments and key insights on investment trends in the robotic surgery sector, based on the most recent news snippets and market research reports: * Robotic surgery market is experiencing strong growth, with the global market projected to reach \$19.5 billion by 2028, growing at a CAGR of 11.0% during the forecast period. * Companies are employing various strategies to drive innovation and growth, including developing their own technology, acquiring existing systems, and forming strategic partnerships. * Notable acquisitions include Stereotaxis' acquisition of Access Point Technologies and Asensus Surgical's ongoing merger activities. * Significant investments have been reported in the digital surgery technologies market, with companies like Medical Microinstruments, Fabric, and HealthSnap raising substantial funds to commercialize their surgical robotics platforms. * Media coverage remains positive, with a focus on the growth potential and opportunities in the field of robotic surgery. * Key players in the sector include Intuitive Surgical, Medtronic, Stryker, and Zimmer Biomet Some specific findings from the media coverage analysis include: * Nami Surgical secured \$4 million in investment and grant funding to develop its ultrasonic platform for robotic-assisted surgery. * The digital surgery technologies market is projected to reach \$5,084.7 million by 2032. * The US market for robotic surgery was valued at \$1.8 billion in 2022 and is expected to grow from \$6.4 billion in 2030 to an annual growth rate (CAGR) of 17.3%. I hope you find this information helpful and insightful. If you have any questions or require further clarification, please do not hesitate to ask. Best regards, \[Your Name] # Negative News Screening Source: https://docs.bigdata.com/app/use-cases/portfolio-management/negative_news_screening ## Insights from ESG Controversies Affecting Investments Controversial events may impact the performance and reputation of public and private companies. Bigdata tracks in real time 171 ESG controversies such as lawsuits, product recalls, or regulatory changes, across 40,000 curates sources. To showcase Bigdata's capability to screen for negative news, we've created a diverse portfolio of 10 companies across different sectors: | Company | Sector | | -------------------------- | --------------- | | Tesla Inc. (TSLA) | Automotive | | JPMorgan Chase & Co. (JPM) | Banking | | Pfizer Inc. (PFE) | Pharmaceuticals | | Walmart Inc. (WMT) | Retail | | ExxonMobil Corp. (XOM) | Energy | | Meta Platforms Inc. (META) | Social Media | | Airbus SE (AIR) | Aerospace | | Disney (DIS) | Entertainment | | General Electric (GE) | Industrial | ## Negative News Summary For a quick overview of the recent negative news impacting the portfolio, let's ask Bigdata to identify main negative news connected to the selected companies for the past month: > Provide a short report of recent negative news for the following companies in my portfolio: Apple Inc. (AAPL), Tesla Inc. (TSLA), JPMorgan Chase & Co. (JPM), Pfizer Inc. (PFE), Walmart Inc. (WMT), ExxonMobil Corp. (XOM), Meta Platforms Inc. (META), Airbus SE (AIR), Disney (DIS), and General Electric (GE). Include any major ESG controversies or events from the past month. ### Apple Inc. (AAPL) * Negative sentiment due to analyst downgrades and iPhone/China concerns. * Recent earnings positive, but growth expectations weigh on stock. * No major ESG controversies reported recently. ### Tesla Inc. (TSLA) * Declining US demand due to CEO's image and safety issues. * Slowing growth, price cuts, and poor stock performance. * No major ESG controversies reported recently, but concerns over Musk and environmental impact exist. ### JPMorgan Chase & Co. (JPM) * No recent negative news or ESG controversies. * Past criticism for controversial deals and handling of 2008 crisis, but no recent reports. ### Pfizer Inc. (PFE) * Q1 revenue decline due to operations and currency impact. * Oncology biosimilar revenue down due to lower US pricing. * Maintained 2024 revenue guidance, raised adjusted EPS guidance. * No major ESG controversies reported recently, but past criticism for pricing practices and opioid crisis exists. ### Walmart Inc. (WMT) * Internal system failure in March caused mispricing at stores. * Widespread criticism and lower share prices due to the issue. * No major ESG controversies reported recently, but past criticism for labor practices and community impact exists. ### ExxonMobil Corp. (XOM) * Investor backlash due to legal actions against climate activists. * Upward earnings estimate revisions for 2024 and 2025. * Strong Zacks Style Score for Value and Momentum. ### Meta Platforms Inc. (META) * No specific negative news or ESG controversies reported recently, but past criticism for user data and mental health impact exists. ### Airbus SE (AIR) * No specific negative news or ESG controversies reported recently, but past criticism for arms deals and environmental impact exists. ### Disney (DIS) * No specific negative news or ESG controversies reported recently, but past criticism for labor practices and sexual misconduct allegations exists. ### General Electric (GE) * No specific negative news or ESG controversies reported recently, but past criticism for pension obligations and controversial deals exists. **Tip**: Click on the "Show Audit trail" icon at the bottom of the response to see how Bigdata breaks down your prompt and gathers the information necessary to get you an answer. ### Looking Closer at Specific Controversies Now that we have this general overview, let's ask Bigdata for more detailed insights into specific controversies, to have a better grasp on the potential impact on the company's operations, reputation, and stock performance. > For ExxonMobil, can you explain the specific legal actions against climate activist investors and the potential consequences? * ExxonMobil sues investor groups Follow This and Arjuna Capital over a shareholder vote on emission reduction measures. * The proposal aimed to accelerate emission reductions and require targets for "Scope 3" emissions (emissions from a company's value chain). * The lawsuit alleges investor tactics aim to silence voices and disrupt shareholder democracy. * Investors view climate change as a threat to long-term investment and argue ExxonMobil's lawsuit could negatively impact corporate governance. * The investors withdrew the proposal after the lawsuit was filed. * CEO Darren Woods vows to protect annual meetings from "serial attacks" by activists. * The company accuses investors of a "Trojan horse" strategy to deliberately harm the company. * The lawsuit's outcome could impact corporate governance and shareholder influence on ESG issues. * The case highlights the growing tension between companies and activist investors over ESG agendas and shareholder proposals. ### Analyzing Market Trends But is this controversy specific to ExxonMobil, or does it have broader implications? This insight can be helpful if you want to identify market risks or to make sector-specific investment decisions. > Are there any broader market risks or trends that could be exacerbated by the ExxonMobil controversy? * ExxonMobil's lawsuit against climate activists raises concerns about its relationship with investors and reputation. * Increased investor focus on ESG issues could negatively impact companies perceived as lacking in accountability and proactive climate action. * Geopolitical tensions and instability could disrupt trade, cause political instability, and disrupt supply chains, impacting the global economy and markets. * Debate on shareholder rights and corporate responsibility related to climate change could lead to increased regulation and compliance costs for companies, especially those reliant on fossil fuels. * The specific outcome and broader market impact of the ExxonMobil controversy depend on the legal interpretation and situation details. * This case highlights the importance of companies addressing ESG issues and the potential consequences for inaction. # Working with Earnings Transcripts Source: https://docs.bigdata.com/app/use-cases/portfolio-management/working_with_earnings_transcripts ## Get key insights from transcripts Bigdata can summarize call transcripts for over **40,000 publicly-listed companies**, dating back to 2003. In this scenario, let's say you're an investment analyst at a firm considering investing in Tencent. Attending every earnings call for every company you're interested in isn't feasible. Bigdata can quickly summarize key financial metrics from the latest Tencent earnings call, such as revenue, earnings per share, and gross margins. This gives you a clear picture of Tencent's current financial performance without having to spend hours combing through transcripts. You can use either the company name or ticker symbol. ## Summarizing key financial metrics > Summarize Tencent's financial performance for the past quarter, including revenue, earnings per share (EPS), and gross margins. Tencent reported a strong financial performance for the first quarter of 2024. The company's net profit rose 62% year-on-year to 41.89 billion yuan (\$5.79 billion), exceeding analysts' expectations. Revenue for the period grew 6% from a year earlier to 159.50 billion yuan. Gross profit margin expanded significantly, increasing from 45% in the previous year to 53%. This growth was driven by high-margin businesses such as short videos and mini games embedded in its super app WeChat. The gross profit margin improvement led to a 23% increase in non-GAAP gross profits and a 54% increase in adjusted net income available to common shareholders. Earnings per share (EPS) also saw a substantial increase, with earnings per share at 4.386 yuan, up 66% from the previous year's 2.639 yuan. ## Comparative analysis You can also ask Bigdata to compare the performance of a company between quarters, which can be useful to expedite blackline reporting, > Compare Tencent's financial performance from the latest earnings call to the previous quarter. Identify any major changes in key metrics like revenue growth or profitability. Based on the information I have, Tencent reported a 6% increase in revenue for the first quarter of 2024 compared to the same period last year. The company's non-GAAP net profit grew by 54% year-on-year. Gross profit was up 23% year-on-year, and gross profit margin expanded to 53%. Tencent's online ad revenue grew by 26%, and revenue from its online advertising business was the fastest growing segment. The company's profit attributable to equity holders of the company was up 62% year-on-year, marking the fastest growth since the March quarter of 2021. Compared to the previous quarter, Tencent's revenue growth rate remained consistent, but its profitability improved significantly. Its net profit grew at a faster rate than its revenue, and its gross profit margin expanded. The company's online ad revenue continued to grow, driven by the growth of WeChat and its AI-driven advertising technology platform. It is worth noting that Tencent has posted six consecutive quarters of gross profit growth, with gross profit growing faster than revenue, and gross profit growing more than 20% for four consecutive quarters. This growth was supported by high-margin businesses, such as short videos and mini games embedded in its super app WeChat. However, domestic game sales declined amid a lack of meaningful title releases during the period. or against the rest of its sector, to establish a benchmarked comparison: > Compare Tencent's latest earnings performance against its sector peers to establish a benchmarked comparison. Tencent reported a 6% increase in revenue and a 54% increase in non-GAAP net profit year-on-year for the first quarter of 2024. Its gross profit grew by 23% year-on-year, and gross profit margin expanded to 53%. Tencent's online ad revenue grew by 26%, and revenue from its online advertising business was the fastest growing segment. Baidu reported a one percent increase in revenue year-on-year to \$4.4 billion in the first quarter of 2024. Net profit during the same period decreased six percent year-on-year to \$755 million. Alibaba reported a 7% increase in revenue year-on-year to \$30.73 billion in the fiscal year ended March 31, 2024. Net income rose modestly by 9 percent to \$9.9 billion. NetEase reported a 7.2% increase in revenue year-on-year to \$26.9 billion in the first quarter of 2024. Adjusted net profit grew 12% to CNY8.5 billion. Comparing Tencent's latest earnings performance with its sector peers, Tencent's net profit growth rate was higher than Baidu and Alibaba, but lower than NetEase. Tencent's revenue growth rate was lower than Alibaba and NetEase, but higher than Baidu. ## Drilling down Storytelling with top-line financials is only half the battle. Bigdata allows you to zoom in on specific segments, subsidiaries, or markets. This can uncover opportunities that high-level numbers might miss. Follow sources: Click on the "Show Audit trail" icon at the bottom of the response to see how Bigdata breaks down your prompt and gathers the information necessary to get you an answer. > Compare Tencent's latest earnings performance against its sector peers to establish a benchmarked comparison. Tencent reported a 6% increase in revenue and a 54% increase in non-GAAP net profit year-on-year for the first quarter of 2024. Its gross profit grew by 23% year-on-year, and gross profit margin expanded to 53%. Tencent's online ad revenue grew by 26%, and revenue from its online advertising business was the fastest growing segment. Baidu reported a one percent increase in revenue year-on-year to \$4.4 billion in the first quarter of 2024. Net profit during the same period decreased six percent year-on-year to \$755 million. Alibaba reported a 7% increase in revenue year-on-year to \$30.73 billion in the fiscal year ended March 31, 2024. Net income rose modestly by 9 percent to \$9.9 billion. NetEase reported a 7.2% increase in revenue year-on-year to \$26.9 billion in the first quarter of 2024. Adjusted net profit grew 12% to CNY8.5 billion. Comparing Tencent's latest earnings performance with its sector peers, Tencent's net profit growth rate was higher than Baidu and Alibaba, but lower than NetEase. Tencent's revenue growth rate was lower than Alibaba and NetEase, but higher than Baidu. For an edge on the company's future direction, ask Bigdata to identify strategic shifts mentioned in calls, like mergers, new product launches, or market expansions: > Did the latest Tencent earnings call discuss any international expansion plans? Are there specific markets or regions they are focusing on for growth, and how are they tailoring their strategies for those markets? Based on the information I have, the latest Tencent earnings call did not explicitly discuss international expansion plans in detail. However, the company mentioned the growth of its international market in the Value-added Services segment, specifically in the gaming sector. The release of new games, such as "Dungeon & Fighter Mobile," is expected to contribute to growth in the international market. Earnings calls are often packed with technical terms and industry jargon, which can be confusing. Bigdata can act as your translator, for more clarity: > In the call, they mentioned 'mini-games' contributing to VAS revenue growth. Can you explain the concept of mini-games within the WeChat ecosystem and their role in monetization? Mini-games within the WeChat ecosystem refer to small, simple games that are integrated into the popular messaging app. These games are developed by Tencent and other developers, and they are accessible to WeChat users through mini-programs. Mini-games have become a core strategy for Tencent, contributing significantly to the growth of its Value-added Services (VAS) segment. The revenue from mini-games comes from various sources, including advertising, in-app purchases, and revenue sharing. The integration of mini-games into WeChat provides several benefits for Tencent. First, it helps to increase user engagement and retention within the app. Second, it diversifies Tencent's revenue streams beyond gaming, which has been facing regulatory challenges in China. Finally, it leverages WeChat's massive user base and social network to monetize the games effectively. The revenue potential of mini-games is substantial. According to MoonFox Data, the overall revenue of WeChat mini-games has surpassed 10 billion yuan. As more mid- and large-sized game companies enter the mini-game market and integrate their games into the platform, the growth potential of this business is enormous. ## Getting the bigger picture Let's also ask Bigdata for insights on how regulations might impact Tencent, which is helpful if you need to assess its growth strategies within a dynamic regulatory landscape. > What is the current regulatory landscape in China, specifically concerning data privacy or anti-trust concerns and how it can impact Tencent? China's regulatory landscape regarding data privacy and anti-trust concerns has seen significant developments in recent months. The Chinese government has been implementing new regulations to strengthen data protection and address monopolistic practices. China's Personal Information Protection Law (PIPL) came into effect in November 2021, which sets out rules for the collection, processing, and transfer of personal information. In March 2024, new regulations on cross-border data flows were published, making it easier for companies to transfer personal data outside of China while ensuring data security and privacy. These regulations aim to provide a legal framework for data transfers and protect individuals' privacy rights. China has also been intensifying its efforts to curb risk in the trust sector and regulate internet companies. In 2020, regulators declared victory in cleaning up China's online peer-to-peer lending industry. More recently, authorities have been focusing on preventing monopolistic practices and promoting fair competition. In January 2024, Tencent faced regulatory scrutiny, leading to a temporary ban on new user registrations for one of its blockbuster games. These regulatory developments can impact Tencent in several ways. The company must comply with the new data protection and cross-border data transfer regulations to ensure the security and privacy of its users' personal information. Additionally, Tencent may face increased scrutiny and potential regulatory action if it is found to be engaging in monopolistic practices or violating competition laws. ## Creating a report Finally, the output can be shaped to your specific needs, within seconds, which saves you valuable hours. > Generate an email summarizing the latest Tencent earnings call. Include key points in bullet format. **Subject: Tencent Earnings Call Summary - Strong Q1 Performance and Regulatory Landscape** Dear \[Recipient], I am pleased to provide you with a summary of the latest Tencent earnings call held on \[2024-05-15]. Below are the key points discussed during the call: * Tencent reported a net profit rise of 62% to 41.89 billion yuan (\$5.79 billion) in Q1 2024, driven by the expansion of high-margin businesses such as short videos and mini games embedded in its super app WeChat. * The company's gross profit margin expanded to 53% from 45% a year earlier, supported by these high-margin businesses. Short videos saw a significant increase in total user time and gross receipts of mini games. Online ad revenue also rose 26%. * Tencent is investing in AI technology, platform enhancements, and high production value content to continue cultivating high-quality revenue streams. The company is due to release its highly anticipated game title "Dungeon & Fighter Mobile" on May 21 in China. * Regulatory developments in China, including the implementation of new data protection and cross-border data transfer regulations, and increased scrutiny on monopolistic practices, can impact Tencent. The company must comply with these regulations to ensure the security and privacy of its users' personal information and avoid potential regulatory action. The regulatory landscape is dynamic, and companies operating in China must stay informed and adapt to the evolving regulatory environment. * Tencent's revenue for 2023 was 609.0 billion yuan (\$84.6 billion), up 10% year-on-year. Despite the challenges posed by regulatory crackdowns in recent years, the company's strong Q1 performance and promising outlook have led to a 30% increase in its shares so far this year. Analysts expect positive earnings revisions and multiples' expansion moving forward. Additionally, Tencent is on track to buy back over 100 billion Hong Kong dollars (\$12.8 billion) of its shares this year and pay higher dividends. Please let me know if you have any questions or require further information. Best regards, \[Your Name] # Assessing supply chain disruptions Source: https://docs.bigdata.com/app/use-cases/risk-analysis/assessing_supply_chain_disruptions Our world is deeply connected, so disruptions can quickly cascade through global supply chains, impacting businesses and consumers alike. Bigdata can help assess the early impact of global developments, such as conflicts, pandemics or natural disasters on supply chains. In this example, we use Bigdata to evaluate how **the Red Sea conflict** might impact certain sectors. ## Understanding the event First, we might want to get a better understanding of what the conflict is all about: > What is the Read Sea Conflict? The Red Sea conflict refers to a series of attacks on commercial vessels, primarily those of Israeli origin, in the Red Sea and the Bab el-Mandeb Strait since late 2023. These attacks have disrupted maritime traffic and oil transportation in the region, which is critical for global commerce as it carries approximately 15% of the world's maritime traffic. The Houthis, a paramilitary group in Yemen, have claimed responsibility for these attacks in response to ongoing conflicts, particularly the war in Gaza. The situation has led to geopolitical tensions, with various countries, including Russia and China, having different stances on the issue. ## Identify Impacted Companies Companies heavily reliant on Red Sea shipping routes are likely to face increased costs, delays, and potential inventory shortages. An early identification would allow for swift adjustments to investment strategies or portfolio allocations. Let's ask Bigdata to identify what companies have mentioned the Red Sea conflict in their recent communications. For this query, Bigdata will browse earning calls, press releases and news. > Identify companies that have mentioned the 'Red Sea conflict' in their public communication within the past 3 months. Focus on companies mentioning potential supply chain disruptions caused by the conflict. Based on the information I have, the following companies have mentioned the Red Sea conflict in their earnings calls, press releases, or public statements within the past 3 months and have discussed potential supply chain disruptions caused by the conflict: Hapag-Lloyd, Maersk, Ardmore Shipping Corporation, EQL Pharma. ## Analyze the impact We can further explore the *specific* concerns of these companies, such as increased shipping costs, extended lead times, or rerouted trade routes. > Assess the impact on different supply chain stages (raw materials, finished goods). Highlight specific quotes from company statements that clearly illustrate the disruption's nature and severity. Based on the information I have, the companies identified have expressed concerns about disruptions to their supply chains caused by the Red Sea conflict. Specifically, they have mentioned increased shipping costs, extended lead times, and affected trading patterns due to the diversion of vessels away from the Red Sea. Some companies have also noted that the conflict may last until at least the second half of the year, or even all of 2024. For example, Hapag-Lloyd has reported that the Red Sea crisis has led to delays, higher costs, and more CO2 emissions due to vessels being diverted around the southern tip of Africa. Ardmore Shipping Corporation has noted that many shipping companies have routed their vessels away from the Red Sea, which has affected trading patterns, rates, and expenses. Maersk has reported that the industry is spending 15% to 20% of its Asia-to-Europe vessel capacity on sailing south of Africa to avoid the Red Sea, and that the conflict is expected to last until at least into the second half of the year. EQL Pharma has reported that its shipping routes were affected by ongoing conflicts in the Red Sea, extending lead times by 2-3 weeks and escalating costs. ## Geographic & Industry Trends With the help of Bigdata, we can also identify regions likely to be most affected, and industries heavily reliant on maritime transportation: > Among the companies impacted by the Red Sea conflict, identify any geographic trends. Are there specific regions or industries that seem to be most concerned about supply chain disruptions? The information I have indicates that the disruptions caused by the Red Sea conflict have affected global supply chains and have led to rising costs and severe disruption for various sectors, including production and retail. The Red Sea is located between Africa, Asia, and Europe, and the disruptions have had ripple effects on these regions. For example, some shipping companies have been diverting journeys away from the Red Sea and opting to make much longer, costlier journeys from Asia via South Africa, threatening to marginalize Mediterranean ports including Italy's. Therefore, it appears that Europe, Asia, and the Middle East are regions that are most concerned about supply chain disruptions caused by the Red Sea conflict. ## Potential opportunities While the Red Sea conflict poses significant disruptions, it is also prudent to explore any potential upsides. For instance, Bigdata can help research alternative logistics providers or geopolitical beneficiaries > Can you identify any companies that might potentially benefit from the Red Sea conflict? This could include companies providing alternative resources, logistics solutions, or risk mitigation strategies. Based on the information I have, some companies that might potentially benefit from the Red Sea conflict by offering alternative resources or transportation routes are: * The Israeli software startup, named Descartes Labs, has developed a new logistics solution that allows ships to bypass the Red Sea and travel through the Suez Canal and the Mediterranean Sea instead. This new land route, which is being used by one of the world's biggest shipping lines, Maersk, could provide an alternative transportation option for companies looking to avoid the disruptions caused by the conflict in the Red Sea. * Mediterranean ports: With many shipping companies diverting their vessels away from the Red Sea and opting for longer, costlier journeys, ports in the Mediterranean Sea could potentially see increased business as vessels are rerouted to avoid the Red Sea. Some of the major Mediterranean ports include those in Italy, Spain, Greece, and Egypt. * Companies with ports around the Cape of Good Hope: With the potential for disruptions to shipping in the Red Sea, companies with ports around the Cape of Good Hope, such as South Africa, could potentially benefit from increased business as vessels are rerouted to avoid the Red Sea. This could include ports in Durban, Cape Town, and Richards Bay. # Bigdata developers blog Source: https://docs.bigdata.com/blog/introduction Insights on AI, research, engineering, and the future of financial intelligence. Bigdata developers blog Welcome to the Bigdata developers blog, where we share what we're building, what we're learning, and where we think the industry is heading. This blog is a space for deep dives into engineering, architecture decisions, research insights, and practical lessons from our work at the intersection of AI, data engineering, and financial intelligence. We write about the tools we use, the systems we design, and the ideas shaping the next generation of data-driven financial technology. Whether you’re a developer integrating our API, a data engineer building pipelines, a researcher exploring financial datasets, or simply curious about how AI is transforming finance, this blog offers a behind-the-scenes look at our work and the challenges we’re solving. *** ## What we write about How artificial intelligence is reshaping financial research, search, and decision-making, and what comes next. Deep dives into the data, models, and methodologies behind Bigdata's knowledge graph and content engine. Technical stories from the team: architecture decisions, scaling challenges, and lessons learned in production. New features, platform updates, and the thinking behind how we build Bigdata products. Culture, milestones, and the people driving Bigdata forward. Announcements, partnerships, and industry coverage. *** ## Latest posts How Workflows keeps financial research reproducible and checkable while the model, not a fixed graph, decides which document to read next. The Entity Sentiment API for trend analysis and backtesting, and the Sentiment Tearsheet for real-time "what's driving this" — live in Claude, ChatGPT, and Copilot. Introducing the Chat Widget and Document Viewer Widget: one-line embeds that put the Research Agent inside any app, with your brand on it. How adaptive planning cuts large-universe Search workflows from minutes to seconds while preserving high-relevance evidence in benchmark screens. Templates, grounded output, and parallel sub-agents so the same research framework runs across your whole coverage universe. How financial institutions can use Claude with Bigdata MCP and Skills to produce consistent, scalable research reports on demand. # Sentiment in Bigdata.com: The Trend and the Story Source: https://docs.bigdata.com/blog/market-data/entity-sentiment-signals

July 20, 2026

Market Data, MCP, Sentiment / 7 minutes read
**TL;DR** * Bigdata.com ships two sentiment tools from RavenPack's research stack: a **daily trend signal** (REST API: backtesting, monitoring, alerts) and a **real-time tearsheet** (zero code, inside Claude, ChatGPT, and Copilot). * They answer different questions, *what's the trend?* versus *what's driving it right now?*: two complementary horizons on the same name, built to be used together. * Every chart and number below comes from live API calls you can reproduce today. **At RavenPack, we use multiple sentiment metrics.** Our EDGE Analytics engine computes a whole family of them, each tuned to a different research question. Bigdata.com adds its own native layer: [chunk-level sentiment](/getting-started/search/chunk_sentiment#sentiment-model), a score on every document chunk from a transformer trained on financial news and corporate event coverage. It measures likely market impact, not linguistic tone, from -1 to +1. This post covers the two tools built on those foundations: a daily trend signal for backtesting and monitoring, and a real-time read on what's moving a name today. Here's the trend lens on Meta over the trailing year: sentiment\_pressure converted into a volatility-scaled band around price: Meta price with sentiment-pressure ribbon, trailing 12 months. Sentiment regime flipped negative on Oct 29, one session before an 11% drop Green is positive sentiment pressure, red is negative, and the band's width scales with the stock's own volatility. Meta's sentiment\_pressure turned negative on **October 29**, one session *before* an 11% drop, and stayed red through the entire drawdown. One flip doesn't make a strategy, but the signal is daily, point-in-time, and years deep: whether it repeats across your universe is a testable question. ## Two tools, two questions | | **Entity Sentiment API** | **Sentiment Tearsheet** | | ----------------------- | ---------------------------------------------------------- | ---------------------------------------------------------------------- | | **Question it answers** | "What's the trend over time?" | "What's driving sentiment right now?" | | **Update cadence** | Daily, historical depth | Real-time, 90-day rolling window | | **Data pipeline** | EDGE Analytics: events, relevance, novelty, source ranking | Bigdata.com chunk-level sentiment: news-only, recency-decayed evidence | | **Best for** | Backtesting, portfolio monitoring, programmatic alerts | Morning briefings, "why did this move," analyst research | | **How you use it** | A few lines of Python against a REST endpoint | Ask Claude, ChatGPT, or Copilot in plain language | | **Audience** | Developers, quants, data engineers | Analysts, PMs, anyone who wants an answer without writing code | A trend signal that reacted to every headline would be too noisy to backtest. A real-time read refreshed once a day would miss the story as it develops. Two jobs, two signals, one research stack. ## Tool 1: Entity Sentiment API, the trend The `/v1/entity-sentiment/` endpoint returns three signals per entity per day: **daily\_sentiment** (today's weighted tone), **sentiment\_pressure** (is the 90-day trend unusual for this company), and **abnormal\_media\_attention** (is coverage volume unusual). Reach for it to look back over months or years, or to backtest against price. **Daily sentiment** is the day's weighted average of event sentiment, weighted by `(relevance/100)² × (novelty/90)²`: a highly relevant, novel event counts far more than a marginal or repetitive one. **Sentiment pressure** z-scores the 90-day moving average against the company's own trailing year, normalized to \[-1, 1]. Beyond ±0.9 is statistically unusual. It answers: *is the recent trend better or worse than this company's norm?* **Abnormal media attention** applies the same treatment to coverage *volume* instead of tone: a bad story spreading and a product launch both spike it, for opposite reasons. The full EDGE Analytics pipeline (relevance and novelty weighting, bias correction, subsidiary rollup, z-scoring, normalization) ships as one endpoint. None of it is yours to maintain. ```python theme={null} import httpx import pandas as pd response = httpx.post( "https://api.bigdata.com/v1/entity-sentiment/", headers={"X-API-KEY": "YOUR_API_KEY"}, json={ "identifier": {"type": "rp_entity_id", "value": "4A6F00"}, # Alphabet Inc. "timestamp": {"start": "2025-07-20", "end": "2026-07-20"}, }, ) df = pd.DataFrame(response.json()["results"]["values"]) ``` One year of daily signals in a DataFrame. The tail, as returned today: | date | daily\_sentiment | sentiment\_pressure | abnormal\_media\_attention | | ---------- | ---------------: | ------------------: | -------------------------: | | 2026-07-17 | 0.121 | 0.086 | 0.794 | | 2026-07-18 | 0.150 | 0.063 | 0.792 | | 2026-07-19 | 0.218 | 0.071 | 0.777 | `identifier.value` also accepts a list: one call covers your whole watchlist. ## The overlay, across a basket The same ribbon across eight names over the trailing 12 months, each panel annotated with the correlation between sentiment\_pressure and price: Price with sentiment-pressure ribbon for an 8-company basket, trailing 12 months, with per-company correlation ``` band(t) = price(t) × (1 + scaling(t) × sentiment_pressure(t)) scaling(t) = VOL_MULTIPLIER × ewma_volatility(t, halflife=10 days) ``` Volatility scaling keeps the band proportionate whether a stock is quiet or choppy. Meta tracks tightest (r = +0.81); Netflix, Oracle, and Tesla follow (+0.60, +0.55, +0.55). Oracle's ribbon flips red at its September peak and stays red through the slide; Microsoft sits at +0.23. The relationship is company-specific: measure it per name before you lean on it. Daily history is what makes that possible. ## Continuously monitoring private companies Private companies in the Bigdata.com knowledge graph get the same signals, driven by funding rounds, launches, and regulatory scrutiny instead of earnings cycles. Watch abnormal media attention around SpaceX's IPO: SpaceX Abnormal Media Attention, year to date 2026, with the June 12 IPO marked Coverage ran well below SpaceX's norm in January, crossed above normal in April, and hit the abnormal band before the June 12 listing. The build-up preceded the IPO by weeks, and the signal ran straight through it: the entity ID doesn't change when a company lists. Same call as any public name: ```python theme={null} json={"identifier": {"type": "rp_entity_id", "value": "335CF4"}, # SpaceX "timestamp": {"start": "2026-01-01", "end": "2026-07-20"}} ``` ## Twenty years of one company's sentiment One request covers up to 3,650 data points, about 10 years per entity; stitch calls together for more. Apple's price with its sentiment-pressure ribbon, weekly, 2006 through today: Apple Inc. price with sentiment-pressure ribbon, weekly, 2006 to 2026, log scale The red troughs line up with the real drawdowns: 2008, the early iPhone-era dips, 2013, 2016, the 2018 selloff, COVID, the 2022 bear market. That depth makes the signal testable rather than anecdotal: backtest across regimes, don't eyeball one good call. ## Tool 2: Sentiment Tearsheet, what's driving it right now The trend API looks back. When you need to know *why* a stock is moving today, you want the news itself, ranked by what's driving the current reading, with a narrative that ties it together. That's the Sentiment Tearsheet. It lives inside Claude, ChatGPT, and Microsoft Copilot through the Bigdata.com MCP connector. No API key, no code: ask "what's driving sentiment on SpaceX right now?" and it answers. Its building block is the [chunk-level sentiment](/getting-started/search/chunk_sentiment#sentiment-model) introduced above, aggregated into a company-level signal. The same scores come back on every Search API result, so anything the tearsheet summarizes you can drill into chunk by chunk. Three design choices keep the signal clean. SEC filings and transcripts are excluded: boilerplate carries systematic sentiment bias, not news. Near-neutral coverage is dropped and strong coverage is weighted by squared magnitude, so the score is decisive. And evidence is ranked by contribution to *today's* reading (relevance, magnitude, recency), not raw relevance. ### SpaceX, called just now We saw SpaceX through the trend lens earlier. Here it is through the real-time lens, today. Everything below is the tool's actual output.
Space Exploration Technologies Corp. SPCX · 90-day lookback
Sentiment −0.30 · slightly negative momentum −0.13 · strong downward sentiment z (1mo/1qt) −1.9 / −2.2 · unusually low attention −45.8% · z −1.4 / −0.2

Summary

SpaceX's post-IPO equity narrative is dominated by near-term Starship execution setbacks and the resulting market repricing. Multiple reports tie the stock slide to the postponed and aborted Flight 13 and engine ignition issues. Coverage also carries a genuine counterweight in AI compute and supply-chain themes, but the current regime is negative and deteriorating: -0.303 against a -0.175 baseline, momentum -0.129, and a quarterly z-score of -2.2, beyond the ±2 threshold the tool flags as statistically unusual.

Bullish

  • Foxconn reported to secure AI server manufacturing order from SpaceX (about USD 52B)
  • Quiet build-out of an AI compute rental business: Google, Anthropic, Pentagon deals
  • Dip-buying framing emerging: "down 45% from its high, history suggests..."

Risk / Watchlist

  • Starship Flight 13 aborted after four engines failed to ignite; retry set for Jul 23
  • Stock below its USD 135 IPO price; about USD 1T of market value lost from the post-IPO peak
  • FT: traders raising bets against SpaceX; \~30% of the public float shorted

Outlook

The unresolved tension: can Starship execution recover fast enough to restore the post-IPO valuation trajectory, or does the market keep discounting execution variability? Evidence supports both sides; no specific forward view.

Evidence, ranked by contribution to today's reading (relevance x |sentiment| x recency decay)

Headline Source Date Sent Contrib
SpaceX stock wobbles after Starship launch postponement InvestingCube Jul 20 −0.79 −0.53
Weeks after record IPO, SpaceX loses USD 1 trillion in market value Times of India Jul 19 −0.80 −0.47
SpaceX stock is down 45% from its high; history suggests... Nasdaq Jul 20 +0.83 +0.44
Foxconn secures AI server contract manufacturing order from SpaceX Wallstreetcn Jul 20 +0.82 +0.38
Four engines fail to ignite, forcing SpaceX to abort Starship launch MSN Jul 19 −0.70 −0.33
Beyond rockets, SpaceX is quietly renting AI compute Fortune Jul 19 +0.69 +0.32
SpaceX stock falls below its USD 135 IPO price Wealth Professional Jul 20 −0.55 −0.26
Traders are increasingly betting against SpaceX Financial Times Jul 18 −0.61 −0.20

Contrib: contribution to the current reading, computed as relevance x |sentiment| x recency decay. A month-old FT story about the USD 400B value drop scores near zero here; this weekend's launch abort dominates.

Read the two horizons together. The trend lens says the 90-day regime is solidly positive: months of pre-IPO enthusiasm are still in that window, and one bad weekend doesn't undo a trend. The real-time lens says the news cycle turned sharply this weekend, and shows you the exact articles. The trend tells you where the name stands; the tearsheet tells you what's moving it now. Before the open, you want both. ### How to try it No setup beyond connecting Bigdata.com to your assistant of choice: * Tool reference: [Sentiment Tearsheet](/mcp-reference/tools/bigdata-sentiment-tearsheet) * Connect it to Claude: [Claude MCP integration guide](/mcp-reference/oauth-integrations/claude-mcp-integration) * Connect it to ChatGPT: [ChatGPT MCP integration guide](/mcp-reference/oauth-integrations/chatgpt-mcp-integration) * Microsoft Copilot and other agentic platforms: [MCP introduction](/mcp-reference/introduction) Once connected, just ask. Developers can call it programmatically (`find_securities`, then `bigdata_sentiment_tearsheet`), but the point is that you don't have to. ## Choosing between them Use the **Entity Sentiment API**. Pull `sentiment_pressure` historically across your universe, join it to price, and test it like any other signal. Use the **Entity Sentiment API**. Daily batch pulls, rank by `sentiment_pressure` change, flag `|sentiment_pressure| > 0.9` for review. Use the **Sentiment Tearsheet**, inside Claude, ChatGPT, or Copilot. Ask in plain language, get the narrative and the sources behind it in seconds. Use the **Sentiment Tearsheet**. No code, no API key: just ask your assistant what's driving sentiment on each name before the market opens. ## Try it on your own book Everything above came from live API calls. The fastest way to evaluate the signals is against names you actually cover. * **Zero-code start**: [connect the Bigdata.com MCP to Claude or ChatGPT](/mcp-reference/introduction) and ask for a sentiment tearsheet on any name in your portfolio. Two minutes, no key. * **API access**: [request an API key](https://bigdata.com/api?request_access=t) and pull `sentiment_pressure` history for your universe; the [Entity Sentiment API reference](/api-reference/market-data/entity-sentiment) has the full schema. * For bulk historical pulls across large universes, see the [Smart Batching guide](/blog/search/smart-batching-universe-scale-screening). *** This content is for informational purposes only and does not constitute investment advice. ***
Francisco Gomez

Francisco Gomez

Manager of Applied Intelligence (VP)

Andres Diaz

Andres Diaz

Senior Structured Data Manager

# How to Automate Portfolio Research with Claude Cowork and Bigdata Source: https://docs.bigdata.com/blog/mcp/claude_cowork_with_bigdata

March 18, 2026

Claude Cowork, Bigdata Plugin / 5 minutes read
Portfolio Managers can now automate portfolio research with Claude Cowork and the [Bigdata.com Plugin](/mcp-reference/plugins/bigdata-com), a connector that gives Claude direct access to Bigdata's **Search engine** and **Knowledge graph**. A single scheduled task runs every morning, identifies the top market-moving topics, assesses their impact on each holding, and delivers individual PDF briefs with inline attribution. The result: you open your laptop, launch Claude, and by the time you have your coffee the analysis is done. It is 6:45 AM. You open your laptop and launch Claude. That is all it takes. Within seconds, your scheduled Cowork task kicks off. While you make your coffee, check your messages, or get ready for the day, Claude is scanning the last 24 hours of financial news, identifying the five topics most likely to move markets today, cross-referencing each one against every company in your portfolio, scoring the potential impact, and generating a detailed PDF brief for each holding. By the time you sit back down, the analysis is waiting in a folder on your desktop. ## Why does morning research take so long? Every Portfolio Manager knows the routine. Markets open, and the first hour is a scramble: skimming headlines, checking overnight moves, trying to connect scattered data points to the positions that matter. The table below shows where that time typically goes: | Manual task | Time spent daily | Automated equivalent | | :----------------------------------- | :--------------- | :----------------------------------------------------------------------------------------------------------- | | Scanning news for relevant topics | 30-45 min | Claude Cowork searches via [Bigdata search](/getting-started/search/overview) in seconds | | Mapping topics to portfolio holdings | 20-30 min | [Knowledge graph resolution](/mcp-reference/tools/find-securities) matches tickers to entities automatically | | Drafting impact notes per company | 60-90 min | PDF reports generated with inline source attribution | | Updating tracking spreadsheets | 15-20 min | Spreadsheet updated with scores and confidence levels | | **Total** | **\~2-3 hours** | **\~10 minutes (unattended)** | The information is out there. The problem is that assembling it into something actionable takes too long when done manually, every single morning. ## How does Claude Cowork automate portfolio research on a schedule? Claude Cowork lets you define tasks that run automatically when you open the application. Combine that with the [Bigdata.com Plugin](/mcp-reference/plugins/bigdata-com), which bundles the [Bigdata MCP connector](/mcp-reference/introduction) and [financial research analyst Skills](/skills-reference/mcp-helpers/financial-research-analyst), and you get an autonomous research assistant that delivers a structured portfolio impact analysis every morning. Here is what the workflow produces: | Output | Description | | :---------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------- | | Top 5 market-moving topics | Identified from the last 24 hours using Bigdata's [search engine](/getting-started/search/overview), which indexes thousands of premium financial sources | | Impact assessment per company | Each topic scored for relevance, direction, and confidence against every holding in your portfolio | | Individual PDF reports | One brief per company with detailed analysis and inline attribution linking back to original documents | | Updated portfolio spreadsheet | A single summary view with impact scores, confidence levels, and topic mappings | Scheduled task running ## What does the setup look like? The entire configuration takes minutes. You provide an Excel file listing the companies in your portfolio, just the ticker and the company name. Claude handles the rest. Portfolio template Once the scheduled task runs, it creates a timestamped folder containing a PDF brief for each company and an updated copy of your spreadsheet with impact scores, confidence levels, and topic mappings filled in. Portfolio analysed Under the hood, Claude uses the [Bigdata knowledge graph](/getting-started/knowledge_graph/introduction) to resolve each ticker to its canonical entity via [find\_securities](/mcp-reference/tools/find-companies), then runs targeted searches through the [Bigdata search service](/getting-started/search/overview) to retrieve the most relevant news for each holding. Every claim in the PDF report links back to its source through inline attribution, so you can verify any insight in seconds. These are some examples of the daily briefs generated by the workflow: