For solo developers
Use an AI agent without becoming its QA department
You run Claude Code or Cursor on your own repo and you are the only person who checks the result. Excellent runs beside the agent, checks the work against evidence you can read, and hands back a receipt instead of a confident summary.
The problems
Three things solo developers keep telling us
01
The agent produces a plausible patch faster than you can prove whether it works, so you read the whole diff anyway.
02
You rerun the same commands by hand after every attempt and still miss the case you did not think to check.
03
When an approach finally works, nothing records why — the next task starts from scratch.
Outcomes
What verified agent work looks like for you
The claim and the check are separate
The agent's "done" is recorded as a claim. What ran, what changed, and what passed is recorded separately, so you read a result rather than a summary.
Failures come back with the failure in them
Returned work names the unmet check and the observed output, so the next attempt starts from evidence instead of a re-prompt.
It stays on your machine
Attempts, artifacts and receipts are written locally. There is no account to create and nothing to upload before you can see a result.
Go and look
The pages that answer this, rather than a claim that we did
- QuickstartThe prerequisites and the two commands, with the output each one prints.
- Claude Code and Cursor setupWiring Excellent to the agent you already run.
- Run the first taskOne real task, start to finish, including what a returned result looks like.
- A sample receiptThe actual record a checked run produces, field by field.
Where it stops
What Excellent does not do for you yet
- macOS and Node.js 22.3 or newer. Windows and Linux are not supported yet.
- There is no desktop app to download — Excellent is a command-line tool today.
- Browser, CI and deployment evidence are experimental. Git and test evidence are the solid ground.
Solutions
Someone else does this work at your company?
Run it on one real task
Install Excellent, point it at the agent you already use, and read the first result before you trust the claim.