Start with one repository
Install Excellent, connect your AI agent, run one real task, and inspect the result.
Start
- What Excellent doesThe shortest description of the product: Excellent runs next to your AI agents, records each attempt and checks the result with independent evidence.
- InstallInstall the local CLI, service, and browser interface in a repository you already use with your agent, then initialize it with excellent init.
- QuickstartInstall Excellent, wire it to your agent, and read your first checked result.
- Connect an agentUse the agent and model provider you already chose. Excellent attaches to Claude Code, Cursor and other MCP-capable agents as an MCP server.
- Run the first taskStart with one useful task, not a demo. Run a real task with excellent run, read the attempt it records, and know what the exit codes mean.
- Read a resultUnderstand what passed, failed, or could not be checked: read a verification result from the CLI or from inside your agent.
Core ideas
- How verification decidesEvidence, authority, and why a model can never sign off a pass: the six verdicts, what counts as evidence, retries, flaky tests and anti-gaming.
- Agents and versionsTrack the setup used for each attempt. An agent version records how the agent was configured, so every result belongs to one setup.
- Work and attemptsWork is the request; attempts are the tries. How Excellent records each attempt against the repository state and agent setup, and links retries.
- Claims and evidenceDone is a claim, not proof. How Excellent weighs evidence from Git, tests, CI and people, and why a model's judgment can never carry a pass.
- Checks and resultsThe plain result labels used by Excellent: Verified, Returned, Needs a decision and Not checked, and why a check that cannot run stays visible.
- Experiments and candidatesTest better ways of running the agent. Experiments compare candidate setups (instructions, model, tools, retries) against the current one.
- Promotion and rollbackPromote only what holds up. How a candidate agent setup is promoted on held-out evidence, and how to roll back from the promotion receipt.
- ReceiptsVerify what was bound and signed. What a receipt binds, how to check its signature against a key you pin, and what a valid receipt does not prove.
Security and data
Teams
Integrate
- Claude Code and CursorHow Excellent attaches to the agent you already use: the MCP entry the installer writes for Claude Code and Cursor, and how to undo it.
- MCPConnect Excellent to agent tools through MCP, so another tool can read or operate Excellent through the same checked interfaces. Setup and undo.
Reference
- CLI referenceEvery command the installed CLI actually has: setup, account, work, chat and preferences in excellent, plus the excellent-mcp companion binary.
- Sample receiptA real signed receipt, field by field: what each part binds, how to verify it, and what a valid signature does and does not establish.
- Receipt formatThe schema a receipt conforms to, and a verifier you can run on one without installing Excellent.