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

# Choose a workflow

> Start with the shortest Firedrill path for the job you have now.

You do not need to learn every Firedrill concept before getting a useful synthetic backend. Choose the path that matches your immediate goal.

| I want to…                                 | Start with                                           | What you get                                                      |
| ------------------------------------------ | ---------------------------------------------------- | ----------------------------------------------------------------- |
| Give my agent controlled dependencies      | [Start local Tools](/guides/start-local-tools)       | A running backend, data, connection settings, and Inspector       |
| Test one agent behavior                    | [Run your first drill](/guides/run-first-drill)      | A task, assertions, verdict, and reports                          |
| Keep an existing test runner               | [Local TypeScript SDK](/sdk/local-typescript)        | `runDrills()`, per-test setup, and programmatic results           |
| Replace an imported function or SDK method | [Mock dependencies](/guides/mock-dependencies)       | A `mockTool()` adapter for your runner's mock or spy              |
| Build a reusable fake dependency           | [Create a Tool package](/guides/create-tool-package) | A portable Tool contract and conformance suite                    |
| Exercise a visual agent or app             | [Browser testing](/guides/browser-testing)           | Playwright steps, screenshots, optional video, and world evidence |
| Reproduce a failure                        | [Evidence and reset](/concepts/evidence-reset)       | Exact build, seed, report verification, and reset semantics       |
| Let a coding agent set up Firedrill        | [Coding-agent integration](/guides/coding-agents)    | A stable MCP surface and repository skill                         |

## Two valid entry points

<Tabs>
  <Tab title="Start with Tools">
    Use `firedrill init` and `firedrill serve` when you first need a safe dependency. Inspect operations and data, then connect the agent. Add a scenario or drill only when you need repeatability or a verdict.
  </Tab>

  <Tab title="Start with a test">
    Use the template or `runDrills()` when you already know the behavior to verify. Define a target, starting conditions, and assertions, then run the drill in an isolated world.
  </Tab>
</Tabs>

Both paths use the same Tool contracts, world state, and evidence. Starting a backend proves connectivity; running assertions proves agent behavior.