> For the complete documentation index, see [llms.txt](https://developer.harness.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developer.harness.io/ai-evals/guides/overview-3.md).

# SDK Reference

Reference documentation for the harness-evals Python SDK.

The `harness-evals` Python SDK is the code-first path to defining datasets, evals, scorers, and targets, and running them locally or in CI.

***

## What you will learn

* How to install and configure the SDK.
* How to define datasets, evals, and custom scorers in Python.
* How to run evals locally with pytest and forward results to the control plane.