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

# Agent Architecture

> A conceptual view of how requests, Agent configuration, models, context, tools, and Distribution Channels work together.

# Agent Architecture

B-Bot Hub separates the definition of an AI Agent from the experience used to reach it. This page describes that relationship at a conceptual level. It is not a specification of internal services or execution order.

## Main Layers

<CardGroup cols={2}>
  <Card title="User Experience" icon="window">
    A chat or another Distribution Channel receives input and presents the result.
  </Card>

  <Card title="Agent Configuration" icon="user-robot">
    Identity, system instructions, abilities, model choices, and permitted capabilities define the Agent.
  </Card>

  <Card title="Context and Capabilities" icon="toolbox">
    Conversation context, knowledge, apps, tools, modalities, and team members provide task-specific inputs or actions.
  </Card>

  <Card title="Model" icon="microchip">
    The selected model interprets the available context and generates a response or proposes tool use.
  </Card>
</CardGroup>

## Conceptual Request Flow

```text theme={null}
User or system
  -> Distribution Channel
  -> conversation settings and input processing
  -> Agent instructions and available context
  -> selected model
  -> permitted knowledge, tools, apps, or team members
  -> response, file, or proposed action
  -> Distribution Channel
```

Not every request uses every layer. A direct text question may need only instructions and a model. A multi-step DeepAgents request may also use tasks, workspace files, and review points.

## Configuration and Authorization

Instructions tell the model how it should behave. Permissions determine what the surrounding system allows it to access or do. These are different controls.

* Use the system prompt for role, priorities, and behavioral boundaries.
* Use app, tool, and account permissions for access control.
* Use human-in-the-loop review for sensitive proposed actions.
* Use Distribution Channel settings for how an experience is exposed.

<Warning>
  Do not treat a prompt instruction such as "never access private data" as a substitute for technical permissions. Remove access that the workflow does not need.
</Warning>

## State and Context

The context available to a request can include the current conversation, Agent instructions, retrieved knowledge, tool results, and workspace artifacts. Availability and retention depend on the feature and configuration.

Because context is limited and can change:

* Keep instructions concise and resolve conflicts.
* Retrieve only relevant source material.
* Store large intermediate artifacts in workspace files when appropriate.
* Confirm that important state is present before continuing a task.
* Do not assume that information from another session or channel is available.

## Failure Boundaries

Design each layer to handle failure clearly:

* Invalid or unsupported input should produce an actionable message.
* Missing knowledge should produce uncertainty or a request for information.
* Tool failure should not be described as success.
* Sensitive actions should stop at the configured review point.
* The Distribution Channel should communicate the final status to the user.

## Related Concepts

<CardGroup cols={2}>
  <Card title="AI Agents" icon="user-robot" href="/concepts/introduction">
    Learn the vocabulary for Agent configuration.
  </Card>

  <Card title="Lifecycle and Configuration" icon="sliders" href="/concepts/basics">
    Design, test, distribute, and maintain an Agent.
  </Card>

  <Card title="DeepAgents" icon="robot" href="/concepts/deepagents/introduction">
    Understand multi-step workspaces and review controls.
  </Card>

  <Card title="Distribution Channels" icon="share-nodes" href="/essentials/distribution-channels">
    Configure how users and systems reach an Agent.
  </Card>
</CardGroup>