> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bigdata.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Concepts Overview

> How the Bigdata.com Research Agent and Workflows behave at the protocol level, and the order to read these guides.

The Research Agent and Workflows share the same response model: a streaming
sequence of typed events delivered over Server-Sent Events. The four guides in
this section cover the cross-cutting protocol-level behavior that both services
exhibit -- streaming, grounding, errors, and conversation continuity.

If you have not built against the Research Agent or Workflows before, work through
these pages in order. They are self-contained, but each builds on the previous
one's vocabulary.

## Recommended reading order

<Steps>
  <Step title="Streaming responses">
    Start here. Defines the SSE format, every public message type, the typical
    order of events in a request, and a canonical Python handler the rest of the
    docs build on.
    [Read it](/how-to-guides/agents/concepts/streaming-responses)
  </Step>

  <Step title="Grounding and citations">
    How `GROUNDING` references attribute spans of the answer to their source
    documents, the critical buffering rule for offset math, and a worked example
    that turns a streamed response into a Markdown answer with inline citations.
    [Read it](/how-to-guides/agents/concepts/grounding-and-citations)
  </Step>

  <Step title="Error handling">
    The difference between HTTP-level errors and in-stream errors, what each of
    `ERROR`, `TOOL_ERROR`, and `LLM_RETRY` means, and a retry/backoff pattern for
    `429` and `5xx` responses.
    [Read it](/how-to-guides/agents/concepts/error-handling)
  </Step>

  <Step title="Conversation continuity">
    Resuming Research Agent conversations with `chat_id` and checkpoints, the
    `persistence_mode` switch, the `"INITIAL"` reset sentinel, and resuming
    Workflows by `execution_id`.
    [Read it](/how-to-guides/agents/concepts/conversation-continuity)
  </Step>
</Steps>

## What each page covers

| Page                                                                              | You will learn                                                                                                                                       |
| --------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- |
| [Streaming responses](/how-to-guides/agents/concepts/streaming-responses)         | The 11 public message types (purpose, key fields, when each is emitted) and a complete Python handler that dispatches on `type`.                     |
| [Grounding and citations](/how-to-guides/agents/concepts/grounding-and-citations) | The structure of a `GroundingReference`, the cumulative-answer buffering rule, AUDIT linkage, and how to render Markdown footnote-style citations.   |
| [Error handling](/how-to-guides/agents/concepts/error-handling)                   | HTTP error codes, in-stream `ERROR` vs. `TOOL_ERROR` vs. `LLM_RETRY`, an error-aware handler, and a retry/backoff helper.                            |
| [Conversation continuity](/how-to-guides/agents/concepts/conversation-continuity) | `chat_id`, `execution_id`, `from_checkpoint_id`, `checkpoint_id`, `persistence_mode`, the `"INITIAL"` sentinel, and multi-turn / branching examples. |

## Next steps

Once you are comfortable with the concepts, move on to the service-specific
quickstarts and how-to guides.

<CardGroup cols={2}>
  <Card title="Research Agent quickstart" icon="rocket" href="/getting-started/quickstart_guide_research_agent">
    Send your first Research Agent request end-to-end.
  </Card>

  <Card title="Workflows quickstart" icon="diagram-project" href="/getting-started/quickstart_guide_workflows">
    Define and execute your first workflow, inline or by template id.
  </Card>

  <Card title="Non-streaming pattern" icon="hourglass" href="/how-to-guides/agents/research/how_to_non_streaming">
    Consume the stream end-to-end and print the complete answer in one go.
  </Card>

  <Card title="Workflow templates" icon="file-code" href="/how-to-guides/agents/workflows/creating_templates">
    Anatomy of a workflow template, input placeholders, content filters, and research plans.
  </Card>
</CardGroup>