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

# Create an agent

> Use a Claude Code prompt to generate, register, and smoke-test a new agent.

The template repo ships a Claude Code prompt at `docs/create-new-agent.md` (inside your cloned `agent-platform` directory) that handles the mechanical parts of adding an agent: creating the file in `agents/`, registering it in `app/main.py`, restarting the container, and running a smoke test.

## Run the prompt

Open Claude Code in the cloned `agent-platform` repo and paste:

```
Run docs/create-new-agent.md
```

Claude will ask:

1. **What should the agent do?** A one-line description. "Summarize GitHub issues for a given repo," "Triage incoming Slack messages," etc.
2. **What tools does it need?** Pick from Agno's [100+ toolkits](/tools/toolkits/overview) or describe a custom tool.
3. **Any specific instructions?** Tone, format, escalation rules, anything you'd put in the system prompt.

Claude generates `agents/<your_agent>.py`, adds the import and registration to `app/main.py`, runs `docker compose restart`, and hits the new agent's endpoint to confirm it responds.

A simple agent (one toolkit, no custom tools) takes 5–10 minutes. A bespoke agent with custom tools takes longer.

## Test in the AgentOS UI

Open [os.agno.com](https://os.agno.com), select your new agent in the sidebar, and try realistic prompts. Run it through:

* **The golden path.** What you built it for.
* **Edge cases.** Unusual inputs, partial information, ambiguous questions.
* **Adversarial inputs.** Prompt injection, out-of-distribution requests, attempts to make it do something it shouldn't.

Click **Sessions** and **Traces** in the sidebar. Every run is recorded with full message history, tool calls, and timing. This is what powers the iteration loop on the next page.

<Tip>
  Spend 5–20 minutes in the UI before moving on. The runs you generate here produce the container logs that power the improvement loop.
</Tip>

## What just happened

| Action                                  | Where it landed                             |
| --------------------------------------- | ------------------------------------------- |
| Agent definition                        | `agents/<your_agent>.py`                    |
| Registration                            | `app/main.py`                               |
| Endpoint                                | `http://localhost:8000/agents/<your_agent>` |
| Sessions and traces from your test runs | Postgres, viewable in the AgentOS UI        |

## Next

[Improve the agent →](/tutorials/agent-platform/improve-an-agent)