> For clean Markdown content of this page, append .md to this URL. For the complete documentation index, see https://docs.nvidia.com/dynamo/llms.txt. For full content including API reference and SDK examples, see https://docs.nvidia.com/dynamo/llms-full.txt.

# Sweeper Quickstart

<!--
Generated from `aisimulate/docs/sweeper/quickstart.md` by `docs/fern/scripts/sync_aisimulate_docs.py`.
Edit the canonical source instead of this Fern copy.
-->

<Warning>
**Experimental.** Sweeper is intended for evaluation and feedback, not production capacity
planning.
</Warning>

From a source checkout, install AI Simulate and run its neutral example:

```bash
python -m pip install -e ./aisimulate
python aisimulate/examples/sweeper/run_sweep.py \
  --config aisimulate/examples/sweeper/sweep.yaml
```

The example runner returns deterministic metrics so you can inspect orchestration without importing
an application framework. A production composition supplies a `RunnerFactory` that executes real
replay:

```python
from aisimulate.sweeper import SmartSearchConfig, Sweeper

config = SmartSearchConfig.from_yaml("sweep.yaml")
sweeper = Sweeper(runner_factory=my_runner_factory, show_progress=False)
candidates = sweeper.run(config)
```

Set `sweep.parallel_evals` above one to use spawned worker processes. Scripts using that mode must
guard their entrypoint with `if __name__ == "__main__":`.

Next, read the [Tutorial](/dynamo/dev/knowledge-base/modular-components/ai-simulate/sweeper/tutorial) for the complete configuration flow or [Sweep Configuration
Providers](/dynamo/dev/knowledge-base/modular-components/ai-simulate/sweeper/sweep-configuration-providers) to add feature-specific search dimensions.