Getting started checklist

Connect your system, confirm events and run your first evaluation.

For setup and management entirely from a coding agent, see the headless workflow and SDK platform clients.

Copy this into your coding agent

Paste into Cursor, Codex, Claude Code, or another coding agent in your project.

Help me connect this project to Bench using https://docs.usebench.ai/guides/getting-started.
Inspect the repository and explain the app's intended outcome and main AI entry point.
Check GitHub access, then help me set up SDK events and MCP using the linked guides.
Verify each connection with a real result. Tell me which steps still need my account access.

Open Getting started in Bench to see the connections and results already received for your account. Steps update automatically while the page is open.

1. Connect your repository

   Connect GitHub and select a repository. Bench scans its code for AI systems, prompts and tools. You can also begin with SDK events without GitHub.

2. Check your system’s business outcome

   Open an AI system’s Understanding page. Add or correct what success means: for example, “refund an eligible order exactly once” and the relevant refund policy. Bench uses this context to make evaluation criteria relevant.

3. Confirm your SDK connection

   Choose an environment, install the SDK and run a synthetic request. The step completes after Bench receives an event. Creating a key alone is not evidence that instrumentation works. Follow the SDK quickstart.

4. Run and inspect a Bench

   Select Start benching on a system to compare prompts and models. Inspect failed cases and the evidence behind recommendations. Use Real app testing to inspect tests of application behavior and tool effects. See real app testing.

5. Connect your coding agent, optionally

   Connect MCP with sign-in, then ask your agent to list your Bench systems. The checklist confirms a successful authenticated MCP request. An API key created for an agent does not by itself confirm MCP connection.

SDK progress reflects retained events from the last 30 days across your deployments. Choose the environment during SDK setup. It is not a live heartbeat or a claim that every code path is instrumented.