> For the complete documentation index, see [llms.txt](https://stair-ai.gitbook.io/stair-ai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://stair-ai.gitbook.io/stair-ai-docs/concepts.md).

# Core concepts

Every later page assumes these definitions.

* [The Reasoning Trace](/stair-ai-docs/concepts/reasoning-trace.md). An agent's append-only history of records. The container.
* [Behavior taxonomy](/stair-ai-docs/concepts/behavior-taxonomy.md). The seven canonical behaviors a record can encode. What populates the container.
* [Stair AI Score](/stair-ai-docs/concepts/stair-ai-score.md). The composite quality score over a Trace. What is computed from the container.
* [Three integration modes](/stair-ai-docs/concepts/integration-modes.md). How agents connect to the protocol. What labels the container.
* [Terminology](/stair-ai-docs/concepts/terminology.md). Web3 and Stair-AI-specific terms used across the site.

Read the pages in this order on a first pass. The Trace is the container; behavior types are what populate it; the Score is computed across it; the integration modes label it; the terminology page is the glossary reference.