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

# Agents

> Create specialized AI assistants with custom instructions, tools, and automations

An agent is a reusable AI configuration that lives in your workspace. Instead of repeating the same context in every
chat, you define it once — and the agent remembers it every time.

<CardGroup cols={2}>
  <Card title="Agent Tasks" icon="list-check" href="/features/tasks">
    Automate your agents with tasks
  </Card>

  <Card title="Triggers" icon="bolt" href="/features/triggers">
    Schedule and event-based automation
  </Card>
</CardGroup>

***

## What makes an agent

Every agent is built from a few key components:

| Component        | What it does                                                            |
| ---------------- | ----------------------------------------------------------------------- |
| **Instructions** | The system prompt — defines the agent's role, tone, and behavior        |
| **Model**        | Which AI model powers this agent (GPT, Claude, Gemini…)                 |
| **Knowledge**    | Files you upload as context (docs, guidelines, reference material)      |
| **Tools**        | Capabilities you enable — web search, MCP integrations, connected apps  |
| **Tasks**        | Automations attached to this agent — when and how it runs automatically |

***

## Agents vs. plain chats

|            | Chat                   | Agent                              |
| ---------- | ---------------------- | ---------------------------------- |
| Context    | You set it each time   | Defined once, always applied       |
| Reuse      | Start fresh every time | Click to use across your workspace |
| Automation | Not possible           | Tasks let it run automatically     |
| Team       | Personal               | Shared with your workspace         |

Use a plain chat when you need something quick and one-off. Use an agent when you want consistent behavior across many
conversations — or when you want to automate the agent with a task.

***

## Creating an agent

<Steps>
  <Step title="Open the Agents panel">
    In your workspace sidebar, click **Agents** (or the agent icon).
  </Step>

  <Step title="Click New Agent">
    Give it a name that describes its purpose — "Research Assistant", "Code Reviewer", "Daily Digest".
  </Step>

  <Step title="Write its instructions">
    The instructions become the agent's system prompt. Be specific:

    ```
    You are a senior code reviewer. Focus on security, performance, and maintainability.
    Always suggest concrete improvements with code examples.
    Use our team's style guide (attached in knowledge).
    ```
  </Step>

  <Step title="Choose a model">
    Pick the AI model that fits the task. Claude is great for writing and reasoning; GPT-4o for general tasks; Gemini for research.
  </Step>

  <Step title="Add knowledge (optional)">
    Upload files that the agent should always have access to — style guides, API docs, onboarding materials.
  </Step>

  <Step title="Enable tools (optional)">
    Turn on web search, or connect MCP integrations and apps the agent needs.
  </Step>

  <Step title="Add tasks (optional)">
    Go to the **Tasks** tab to automate the agent — run it on a schedule, on demand, or when an event happens.
  </Step>
</Steps>

***

## Agents and tasks

An agent becomes an **automation** when you attach a task to it.

```
Agent (the who + what)
  └── Task (when it runs + where output goes)
        ├── Trigger: every morning at 9am
        └── Output: post to #team-digest channel
```

One agent can have multiple tasks — each for a different automation:

```
Agent: "Research Assistant"
  ├── Task: "Daily digest"     → runs 9am daily → posts to channel
  ├── Task: "Weekly summary"   → runs every Monday → creates new chat
  └── Task: "On demand"        → run when you press a button
```

The agent's instructions and tools stay the same. Each task can add extra instructions on top for that specific run.

<Card title="Learn about tasks" icon="list-check" href="/features/tasks">
  How to set up automations on your agents
</Card>

***

## Sharing agents

Agents in a **shared workspace** are visible to all workspace members by default.

* **Team members** can use any public agent to start conversations
* **Admins and owners** can edit agents created by anyone
* **Private agents** are only visible to you

<Tip>
  Create a shared "Code Reviewer" or "Meeting Notes" agent once, and your whole team benefits from the same consistent
  configuration.
</Tip>

***

## Example agents

<AccordionGroup>
  <Accordion icon="code" title="Code Reviewer">
    Reviews pull requests, catches security issues, and suggests improvements following your team's standards.

    **Model**: Claude 3.5 Sonnet (strong reasoning)
    **Knowledge**: Team style guide, security checklist
    **Tools**: None needed for review
    **Tasks**: Manual — run when you want a review
  </Accordion>

  <Accordion icon="newspaper" title="Daily Digest">
    Gathers updates from your sources every morning and posts a structured summary to your team channel.

    **Model**: GPT-4o
    **Tools**: Web search
    **Tasks**: Schedule — daily at 8am → post to #digest
  </Accordion>

  <Accordion icon="chart-line" title="Weekly Report">
    Compiles metrics, highlights trends, and posts a formatted report every Monday.

    **Model**: GPT-4o
    **Tools**: Connected data apps
    **Tasks**: Schedule — every Monday 9am → post to #reports
  </Accordion>

  <Accordion icon="headset" title="Customer Support">
    Handles first-line support with deep knowledge of your product and policies.

    **Model**: Claude 3.5 Sonnet
    **Knowledge**: Product docs, FAQ, refund policy
    **Tools**: None — response only
    **Tasks**: Manual — run when needed
  </Accordion>

  <Accordion icon="magnifying-glass" title="Research Assistant">
    Deep-dives into any topic, synthesizes sources, and produces structured research briefs.

    **Model**: Claude Opus or GPT-4o
    **Tools**: Web search
    **Tasks**: Manual — run on demand
  </Accordion>
</AccordionGroup>