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

# Concepts

> The building blocks of every Veval integration.

Veval records what your agent does and tests it against those recordings. You work with a small set of objects: traces record a run, steps record the calls inside it, and scenarios, assertions, replay, and snapshots turn recordings into tests.

## Core concepts

<CardGroup cols={2}>
  <Card title="Traces" icon="route" href="/concepts/traces">
    A recorded agent run: input, output, steps, cost, and timing.
  </Card>

  <Card title="Steps" icon="list-tree" href="/concepts/steps">
    A single LLM call or sub-operation within a trace.
  </Card>

  <Card title="Scenarios" icon="list-check" href="/concepts/scenarios">
    A named set of test items run against your agent.
  </Card>

  <Card title="Assertions" icon="circle-check" href="/concepts/assertions">
    Checks that pass or fail a completed run.
  </Card>

  <Card title="Replay" icon="rotate-left" href="/concepts/replay">
    Run your agent against a recorded trace with mocked LLM responses.
  </Card>

  <Card title="Snapshots" icon="code-compare" href="/concepts/snapshots">
    A stored known-good run that new runs are compared against.
  </Card>
</CardGroup>