> For the complete documentation index, see [llms.txt](https://docs.layerlens.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.layerlens.ai/13.3-concepts-library-+-architecture/concepts-library.md).

# Concepts library

Stratix concepts — the mental model behind models, evaluations, judges, scorers, traces, and ECU.

Read these first. The mental model makes the rest of Stratix easy.

<table data-view="cards"><thead><tr><th></th><th></th><th></th></tr></thead><tbody><tr><td><strong>Mental model</strong></td><td>How everything fits together.</td><td><a href="/8.-evaluate-score-the-outputs/mental-model.md">Read</a></td></tr><tr><td><strong>Models and benchmarks</strong></td><td>The building blocks of the catalog.</td><td><a href="/5.-select-pick-the-model/models-and-benchmarks.md">Read</a></td></tr><tr><td><strong>Evaluations</strong></td><td>What an evaluation actually is.</td><td><a href="/8.-evaluate-score-the-outputs/evaluations-1.md">Read</a></td></tr><tr><td><strong>Traces and spans</strong></td><td>The unit of "what did my AI do."</td><td><a href="/6.-build-wire-your-code/traces-and-spans.md">Read</a></td></tr><tr><td><strong>Judges</strong></td><td>LLM-as-a-judge for subjective dimensions, and GEPA.</td><td><a href="/8.-evaluate-score-the-outputs/judges-1.md">Read</a></td></tr><tr><td><strong>Scorers</strong></td><td>Deterministic graders for objective dimensions.</td><td><a href="/8.-evaluate-score-the-outputs/scorers-1.md">Read</a></td></tr><tr><td><strong>Evaluation spaces</strong></td><td>Saved evaluation configs.</td><td><a href="/8.-evaluate-score-the-outputs/evaluation-spaces.md">Read</a></td></tr><tr><td><strong>Public vs Premium</strong></td><td>What each surface owns.</td><td><a href="/5.-select-pick-the-model/public-vs-premium-1.md">Read</a></td></tr><tr><td><strong>ECU credits</strong></td><td>How compute is billed.</td><td><a href="/11.-admin/concepts-ecu-credits.md">Read</a></td></tr><tr><td><strong>BYOK models</strong></td><td>Bring your own LLM endpoint.</td><td><a href="/5.-select-pick-the-model/byok-models.md">Read</a></td></tr><tr><td><strong>Multi-tenancy</strong></td><td>Orgs, multi-org, isolation.</td><td><a href="/7.-observe-see-whats-happening/multi-tenancy.md">Read</a></td></tr><tr><td><strong>Async vs sync workflow</strong></td><td>When work is queued vs immediate.</td><td><a href="/6.-build-wire-your-code/async-vs-sync-workflow.md">Read</a></td></tr><tr><td><strong>Agentic evaluation</strong></td><td>Pre-deploy gates for multi-step agents.</td><td><a href="/8.-evaluate-score-the-outputs/agentic-evaluation.md">Read</a></td></tr><tr><td><strong>Continuous evaluation</strong></td><td>Score live production traffic.</td><td><a href="/7.-observe-see-whats-happening/continuous-evaluation.md">Read</a></td></tr></tbody></table>

## Where to next

* [Workflow](/1.-introduction/the-stratix-workflow.md) — the 6-stage spine that ties concepts together
* [Tutorials](/2.-get-started/all-tutorials.md) — concepts in action
* [Glossary](/glossary.md) — every term defined