> 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/core-concepts/concepts.md).

# Core Concepts

Understand the building blocks of Harness AI Evals, including targets, datasets, metrics, evaluations, and suites.

Learn the building blocks that compose every evaluation in AI Evals.

* [Targets](/ai-evals/core-concepts/targets.md): The AI systems you evaluate (Prompt, App, Static).
* [Datasets](/ai-evals/core-concepts/datasets.md): Golden test cases that define what "correct" looks like.
* [Metrics](/ai-evals/core-concepts/metrics.md): The scoring rubric (47+ built-in metrics across 9 categories).