> For the complete documentation index, see [llms.txt](https://api.docs.blockbrain.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://api.docs.blockbrain.ai/concepts/cortex.md).

# Cortex

The **Cortex** is the conversational runtime and orchestration layer in this stack. It hosts bots (agent configurations), manages conversations ([Data Rooms](/concepts/data-room.md)), accepts user inputs for completions, and aggregates artifacts created during conversations (attachments, emails, notes/insights). Use Cortex as the backend that turns agent definitions, tools, and workflows into a stateful, auditable, user-facing conversation experience.

#### What Cortex does

* **Bot hosting**: Stores and serves bot definitions, including parent/derived bot relationships.
* **Conversation management**: Creates and maintains conversational contexts tied to a bot and participants.
* **Completions**: Accepts user input and streams or returns model responses using the active bot’s configuration.
* **Artifacts**: Surfaces conversation-linked resources like attachments, emails, and notes/insights.
* **Governance**: Provides a single place to enforce auth, sharing, and audit across bots and conversations.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://api.docs.blockbrain.ai/concepts/cortex.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.