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

# Introduction

> Surface Area rebuilds the systems your agent works against as a sealed world, so you can run a candidate version against reality before reality matters.

**Run agents against reality before reality matters.**

Surface Area rebuilds the systems your agent works against — your ledger, your service desk, your identity provider — as a sealed [world](/worlds). Your agent calls the world as often as it likes, and nothing it does reaches a live system. A candidate version replays the situations your production agent already met and comes back scored.

<Info>
  [Get Started](/get-started) installs the command-line tool and walks you to a
  graded run inside a hosted world in about ten minutes.
</Info>

## What makes this different

Most tools in this space report what your agent **did**. Surface Area reports what a version you have not shipped yet **will do**. Deciding whether a change is safe takes somewhere to run it against the same conditions, as many times as it takes for the result to mean something.

## The loop

<Steps>
  <Step title="Build a world">
    Start a world from a connector template, a connector your organization published, or a contract you write yourself. The platform hosts it, serves the vendor's routes, and pins every version. See [Worlds](/worlds).
  </Step>

  <Step title="Give the world its material">
    Instrument your agent and Surface Area records every LLM call, tool call, and nested step as a trace. Those sessions become the rows and the situations a world is built from. See [Tracing](/tracing).
  </Step>

  <Step title="Ask it questions">
    One captured session becomes many [scenarios](/glossary#scenario). Withhold a piece of evidence, poison another, make a tool start failing, push the horizon out, or fork at the turn where it went wrong.
  </Step>

  <Step title="Run a candidate against all of them">
    Every [rollout](/glossary#rollout) is graded by deterministic checks, LLM judges, or humans. The batch is a [run](/glossary#run). The world version and the model are both pinned, so two runs differ by exactly the thing you changed. See [Evaluation & Replay](/evaluation).
  </Step>

  <Step title="Let a gate decide">
    A [gate](/glossary#gate) asks two questions before a build is promoted: did enough rollouts pass, and were there enough of them for the rate to mean anything.
  </Step>
</Steps>

## Start here

<CardGroup cols={2}>
  <Card title="Get Started" href="/get-started" />

  <Card title="Worlds" href="/worlds" />

  <Card title="Glossary" href="/glossary" />

  <Card title="Evaluation & Replay" href="/evaluation" />

  <Card title="Tracing" href="/tracing" />

  <Card title="Python SDK" href="/sdk" />
</CardGroup>

## Six words

The product is built out of six nouns: **world**, **scenario**, **rollout**, **run**, **eval**, and **gate**. Each one uses the one before it. Read the [Glossary](/glossary) first.

## What else is here

**[Worlds](/worlds).** Build one, put data in it, open a session against it, run an agent, and version it as your systems move.

**[Evaluation & Replay](/evaluation).** How a world's runs are scored. Write the criteria a judge grades against, replay real sessions as regression tests, and keep a world's scenarios in one place.

**[Tracing](/tracing).** A few lines of Python capture each call as a trace over OpenTelemetry. Traces are useful on their own, and they are the raw material every world is built from.

**[The gateway CLI](/cli).** Worlds, sessions, data, and runs from a terminal or a continuous-integration job.

**[Python SDK](/sdk).** The tracing decorator, the worlds client, runs, and replay, with a [TypeScript SDK](/sdk-ts) alongside.

## For AI agents

A machine-readable index of this documentation is published at [`/docs/llms.txt`](https://docs.surfacearea.ai/llms.txt) for coding assistants and agents.


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