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

# CLI and CI

> Run evaluate(...) files locally and fail CI when scores miss your bar.

Run eval files with:

```bash theme={null}
promptlayer eval run path/to/evals
```

Pass a file or a directory. The CLI picks up `*.eval.py` and `*.eval.ts` (plus common JS variants).

Set `PROMPTLAYER_API_KEY` in the environment before you run.

## Fail CI on a low score

Set `passing_score` / `passingScore` on `evaluate(...)`. If the overall score is below that bar, the process exits non-zero and CI fails.

```bash theme={null}
export PROMPTLAYER_API_KEY=...
promptlayer eval run ./evals
```

## File layout

```text theme={null}
evals/
  support.eval.py
  weather_agent.eval.ts
```

Put a top-level `evaluate(...)` (Python also has `aevaluate`) in each file. The CLI skips common junk folders such as `.git`, `.venv`, and `node_modules`.