> ## 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.

# Veval documentation

> Veval records every step of your AI agent and tests it against real production runs.

Veval wraps your agent runs and LLM calls to record traces: inputs, outputs, step timing, token counts, and cost. You run scenarios and assertions against those traces in CI to catch regressions before they reach production.

## Why use Veval

* **Every step, recorded.** Each agent run becomes a trace with its steps, inputs, outputs, timing, tokens, and cost.
* **Production traces as regression tests.** Replay a recorded trace with mocked LLM responses for deterministic, free tests, or live, where the model runs with your current prompt and tools return their recorded output, to catch prompt regressions.
* **Strict by default.** If your agent makes a call the recording doesn't have, replay throws instead of calling the live LLM.
* **Regressions you can read.** Snapshots compare a run against a known-good baseline and report changed prompts, tool arguments, and added, removed, or moved steps, with a line diff.
* **Built-in checks.** Assert on errors, step count, cost, duration, outputs, and tool calls, or grade outputs with an LLM judge.
* **Three SDKs, one model.** C#, Python, and Node share the same concepts and method names.

## Get started

> **[Quickstart](https://docs.veval.dev/quickstart.md)**
>
> Install the SDK and send your first trace.

> **[Concepts](https://docs.veval.dev/concepts/overview.md)**
>
> Traces, steps, scenarios, assertions, replay, and snapshots.

> **[SDK reference](https://docs.veval.dev/llm-reference.md)**
>
> Every API in all three languages, on one page.

## Explore

> **[How Veval works](https://docs.veval.dev/how-veval-works.md)**
>
> How traces are recorded, and how replay turns them into tests.

> **[Test with replay](https://docs.veval.dev/guides/replay.md)**
>
> Run your agent against recorded traces with no live LLM calls.

> **[Catch regressions](https://docs.veval.dev/guides/snapshots.md)**
>
> Compare runs against a stored known-good baseline.

> **[Build with AI](https://docs.veval.dev/ai.md)**
>
> Ready-made context for building with AI coding agents.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.