> ## Documentation Index
> Fetch the complete documentation index at: https://docs.trymaitai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Test

> Curate test sets and run them against a model, workflow, or agent (scored by evaluation criteria) before you ship.

**Test** is where you prove a change is good *before* it reaches production. You curate a **test
set**, run it against a model, workflow, or agent, and score the results against
**evaluation criteria**: so you can compare a candidate against a baseline with confidence.

Come here when you want to answer: *"Did my last change make things better or worse?"*

<Note>
  Watching **live** production quality (Sentinels and Monitors) lives under
  [Observe](/observe/overview). Test is for curated, offline evaluation; Observe is for real traffic.
</Note>

## The building blocks

<CardGroup cols={3}>
  <Card title="Test Sets" icon="vial" href="/test/test_sets/creation">
    Type-less sets of `input + expected output` items, built from requests, workflow runs, agent
    tasks, manual entries, or a file.
  </Card>

  <Card title="Test Runs" icon="play" href="/test/test_sets/execution">
    Execute a set against a model, workflow, or agent, then read the results and track regressions.
  </Card>

  <Card title="Test Criteria" icon="list-check" href="/test/test_sets/criteria">
    Reusable checks (deterministic, LLM-judge, or agent-trajectory) that score your Test Runs.
  </Card>
</CardGroup>

## How they fit together

* A **Test Set** is a type-less batch of items.
* A **Test Run** executes that set against a chosen **consumer** (model, workflow, or agent).
* **Evaluation Criteria** score each run, so you can compare baseline vs. candidate and catch
  regressions.

## Where to go next

* Build your first regression suite: [Test Set Creation](/test/test_sets/creation)
* Fix a failure and prevent it from returning: [Quality Loop](/examples/quality_loop)
* Watch live quality instead: [Sentinels](/observe/sentinels/overview) and [Monitors](/observe/monitors/overview)