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

# ML training agent

> Agent trains a scikit-learn classifier in the code-interpreter template, writes a confusion matrix and metrics JSON.

## Use case

Hand a dataset and a training spec to an agent, get back metrics
and a plot. The `code-interpreter` template exists for exactly
this — scikit-learn, pandas, numpy, matplotlib, seaborn are
pre-installed, so training starts in under a second without any
`pip install` detour.

## Template

`code-interpreter` — rich scientific Python stack. Start this for
anything data-science-shaped.

## Run it

```bash theme={null}
export DECLAW_API_KEY=dcl_...
export DECLAW_DOMAIN=api.declaw.ai
export OPENAI_API_KEY=sk-...

python cookbook/examples/openai-agents-ml-model/main.py
```

## Security policy

```python theme={null}
SecurityPolicy(
    injection_defense=InjectionDefenseConfig(enabled=True, sensitivity="medium", domains=["api.openai.com"]),
    network=NetworkPolicy(allow_out=["api.openai.com"]),
)
```

No PII scanning here because the sklearn demo datasets (iris,
wine, digits) don't contain any. For real workloads, add
`PIIConfig(enabled=True, rehydrate_response=True)`.

Network is OpenAI-only. Training on a local dataset doesn't need
any other host; if someone tries to prompt-inject the agent into
calling an exfiltration endpoint, the connection will fail.

## Env isolation

```python theme={null}
envs={
    "MODEL_FAMILY": "logistic_regression",
    "RANDOM_SEED": "42",
    "DATASET": "iris",
}
```

Training runs are parameterized entirely by env. Re-running with a
different `MODEL_FAMILY` requires no prompt change — just env
changes — so the agent's instructions stay deterministic.

## What the agent does

1. `printenv MODEL_FAMILY RANDOM_SEED DATASET`.
2. Load `sklearn.datasets.{iris|wine|digits}`.
3. Train the selected family (`logistic_regression` or
   `random_forest`) with seed \$RANDOM\_SEED.
4. Run 5-fold cross-validation.
5. Save `/workspace/confusion.png` and
   `/workspace/metrics.json` (`accuracy_mean`, `accuracy_std`,
   `classes`, `n_samples`).
6. Return `cat /workspace/metrics.json`.

## Expected output

```json theme={null}
{
  "accuracy_mean": 0.9733,
  "accuracy_std":  0.0249,
  "classes":       ["setosa", "versicolor", "virginica"],
  "n_samples":     150
}
```

## Full source

See `cookbook/examples/openai-agents-ml-model/main.py` in the repo.