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

# Cookbooks: Agents, RL, and Benchmarks

> Complete, runnable cookbook examples you can copy and adapt: coding agents, A2A chat, ops diagnostics, robot benchmarks, RL training, and more.

Cookbooks are complete, runnable projects you can copy and adapt. Each one shows
an environment, an agent, and a grader working end to end, so you can see a whole
evaluation rather than one concept at a time. They all live in the
[`cookbooks/`](https://github.com/hud-evals/hud-python/tree/main/cookbooks)
directory of the SDK repo. The examples below with a **walkthrough** have a full
guide on this site; the rest are best read straight from their source.

## Walkthroughs

<CardGroup cols={2}>
  <Card title="Coding agent" icon="code" href="/v6/cookbooks/coding-agent">
    Run a coding agent against a shell + files environment, graded by tests.
    Source: [`cookbooks/codex-coding`](https://github.com/hud-evals/hud-python/tree/main/cookbooks/codex-coding).
  </Card>

  <Card title="A2A chat" icon="plug" href="/v6/cookbooks/a2a-chat">
    Serve a chat task over the A2A protocol and talk to it from any client.
    Source: [`cookbooks/a2a-chat`](https://github.com/hud-evals/hud-python/tree/main/cookbooks/a2a-chat).
  </Card>

  <Card title="Ops diagnostics" icon="stethoscope" href="/v6/cookbooks/ops-diagnostics">
    An investigation task where the agent integrates evidence into a diagnosis.
  </Card>

  <Card title="Robot benchmark" icon="robot" href="/v6/cookbooks/robot-benchmark">
    Run a VLA policy against a containerized robot sim, graded by task success.
  </Card>
</CardGroup>

## More runnable examples

These ship in the repo without a separate walkthrough. Read the README in each
directory to run them.

<CardGroup cols={2}>
  <Card title="RL training" icon="dumbbell" href="https://github.com/hud-evals/hud-python/tree/main/cookbooks/rl-training">
    On-policy RL: roll out a taskset with the current weights, train on the
    resulting trajectories, and serve the updated weights for the next rollout,
    all under one trainable model string.
  </Card>

  <Card title="Connect Four self-play" icon="table-cells" href="https://github.com/hud-evals/hud-python/tree/main/cookbooks/connect4-selfplay">
    Symmetric self-play GRPO on a 6×7 Connect Four board, training both sides
    from a single rollout.
  </Card>

  <Card title="Fireworks RL training" icon="fire" href="https://github.com/hud-evals/hud-python/tree/main/cookbooks/fireworks-rl-training">
    The RL loop driven through the Fireworks Training API instead of the HUD
    training service.
  </Card>
</CardGroup>