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

# Modes

> The four interaction modes that control how much autonomy the agent has — from full approval gating to fully automated 24/7 operation.

# Modes

Headmaster has four interaction modes that control how much autonomy the agent has and how often it asks for your approval.

| Mode                | Approvals     | Destructive actions | Scheduled |
| ------------------- | ------------- | ------------------- | --------- |
| **Work Along**      | Every action  | Ask                 | No        |
| **Run It Yourself** | No per-action | Ask                 | No        |
| **Hands-Off**       | None          | No ask              | No        |
| **Autopilot**       | None          | No ask              | Yes       |

Switch modes from the mode selector in the composer area. You can also switch mid-conversation — the change applies to the next action, not retroactively.

***

## Work Along

**The default mode.** The agent works alongside you, asking for approval before running tools, writing files, or making external calls. You see every action before it happens.

**Use when:**

* 🔍 Exploring a new codebase and wanting to see what the agent does.
* 🔒 Working on something sensitive (production config, customer data).
* 🎓 Learning from the agent's approach.

**How it works:**

* The agent proposes an action, shows its parameters and expected outcome.
* You click **Approve** to let it run, or **Deny** to stop it.
* Use **Approve always** to greenlight all future calls of the same type for this conversation.

***

## Run It Yourself

The agent handles the task end-to-end without asking for approval on each step. It still asks before doing anything **irreversible**.

**Use when:**

* ✅ You've given a clear task and trust the agent to execute.
* ⚡ The task has many steps and approving each one would be tedious.
* 🔁 Running a well-understood workflow.

**How it works:**

* The agent runs tools and writes files without per-action approval.
* It still asks before destructive actions (delete, overwrite, send, push).
* You can interrupt at any time with the stop button.
* All actions are logged in the conversation transcript for audit.

***

## Hands-Off

Same as Run It Yourself, but the agent does **not** ask before destructive actions either. It just does them and reports what it did.

**Use when:**

* 🤖 Running a well-tested automated workflow.
* 🚶 You're away from the keyboard.
* 🛡️ You've set up guardrails (project folder scoping, allowed tools list) and trust the setup.

**How it works:**

* No approval prompts at all. The agent runs to completion.
* Every action is still logged in the transcript.
* If the agent encounters an error it can't resolve, it stops and reports rather than guessing.

<Warning>
  Hands-Off mode will delete files and run commands without asking. Set it up on well-understood workflows only. Test in Run It Yourself first.
</Warning>

***

## Autopilot

The agent runs on a schedule, 24/7. It picks up tasks from the Schedule, executes them in Hands-Off mode, and delivers results to your configured Channels.

**Use when:**

* ⏰ You have recurring tasks (daily summaries, weekly reports, monitoring).
* 🌙 You want the agent to work while you sleep.
* ✅ You've validated the workflow in Hands-Off first.

**How it works:**

1. The agent wakes on a schedule trigger.
2. It runs the task in Hands-Off mode (no approvals).
3. Results are delivered to the channel you configured (Telegram, email, desktop notification).
4. The agent goes back to sleep until the next trigger.

<Tip>
  Always test a workflow in Hands-Off mode manually before scheduling it in Autopilot. See [The Schedule](/the-schedule) for setup.
</Tip>

***

## Approval gates

In Work Along and Run It Yourself, the agent asks for approval before:

* 🔧 **Running a tool** — web search, code execution, file read/write, MCP call.
* 📁 **Accessing a file outside the project folder.**
* 🌐 **Making a network request** (external API call, HTTP request).
* ⚠️ **Destructive actions** (delete, overwrite, send, push) — asked in all modes except Hands-Off.

The approval prompt shows:

* What the agent wants to do.
* The tool name and parameters.
* The expected outcome.
* **Approve** / **Deny** / **Approve always** (for this conversation) buttons.

***

<CardGroup cols={2}>
  <Card title="Approvals" icon="shield-check" href="/approvals-human-in-the-loop">
    Full details on the approval flow — clarifications, permissions, secret requests.
  </Card>

  <Card title="The Schedule" icon="clock" href="/the-schedule">
    Set up Autopilot with cron-based recurring tasks.
  </Card>
</CardGroup>