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

# System agents

> The four agents Architech ships with: what each one does and the commands you use to call it.

> [!NOTE]
>
> **Early Access.** Commands and behavior can change between releases.

Architech comes with four **system agents**: the Orchestrator, the Architect, the Developer and the
LLM-Whisperer. You talk to the Orchestrator. It hands each piece of work to the right agent and
brings the result back to you.

You can type a command, or just describe what you want in plain English.

## Orchestrator

**What it does.** The Orchestrator is the coordinator. It reads your project board, routes work to
the other agents, dispatches them and tracks their progress. It never builds anything itself.

**When it's used.** Every session starts here. Use it to pick up planned work, send it out and check
on it.

| Command | Use it to |
| - | - |
| `/sync` | Read your project board. |
| `/dispatch <issue-number>` | Send a planned issue and its tasks to agents. |
| `/status` | Check dispatch progress. |

## Architect

**What it does.** The Architect turns what you want into requirements, a design and a set of tasks.
It splits the work so several agents can build in parallel.

**When it's used.** Before anything is built. Use it when a feature needs a plan, or when you want a
design decision made first.

| Command | Use it to |
| - | - |
| `/spec` | Plan a feature: requirements, then design, then tasks. |
| `/system-design` | Design the components, interfaces and data for a change. |

## Developer

**What it does.** The Developer builds the change. It writes the tests first, then the code, and
checks that both pass. It can also review code against your project's rules.

**When it's used.** Once a task is planned. The Orchestrator usually sends it the work for you.

| Command | Use it to |
| - | - |
| `/implement <issue-number>` | Build a task, with tests. |
| `/code-review <pr-number>` | Review a pull request against your project's rules. |

## LLM-Whisperer

**What it does.** The LLM-Whisperer handles AI work: prompts, LLM features and agents. It measures
quality with evals, then improves the prompt or agent one change at a time and keeps only what scores
better.

**When it's used.** Whenever the change is about how a model behaves, not ordinary code.

| Command | Use it to |
| - | - |
| `/implement-agent` | Build an agent: its tools, memory and loop. |
| `/evaluate` | Score an AI feature against an eval dataset. |
| `/optiloop` | Improve a prompt or agent step by step, gated by evals. |

## System agents and your own agents

System agents are read-only. In the `/agents` manager you can see them and their status, but you
can't edit, export, delete or disable them. Open one and you see a notice that its definition is
read-only. You can still dispatch a system agent and steer it while it runs.

Your own agents are separate. Give them their own names, and you edit and manage them as usual.

To tune how system agents work in your project, don't edit them. Put build commands, architecture
constraints and team conventions in [project context](https://docs.mutagent.io/architech/features/project-context.md) and the
rules [/onboard](https://docs.mutagent.io/architech/onboard.md) sets up.

> **[Orchestrator and agents](https://docs.mutagent.io/architech/agents.md)**
>
> How the roles work together, locally and in the Factory.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.