For technical founders
Ship agent-written code without betting the company on its first answer
You are moving fast and agents are already changing real code. Excellent gives each run a proof trail — what was asked, what ran, what changed, what was checked — so the release decision is made from evidence rather than tone.
The problems
Three things technical founders keep telling us
01
The agent says the bug is fixed and you still have to read the diff, guess which checks matter, and decide whether the answer is real.
02
Every failed attempt teaches you something and the lesson disappears into a chat window.
03
You want to hand agents more of the work, but you need a release rule stronger than "the model sounded sure".
Outcomes
What verified agent work looks like for you
Every run ends in a result you can read
The request, the command, repo state, changed files, the checks that ran and the agent's claim land in one compact record.
Promotion stays deliberate
A checked result can be reviewed before it lands. No agent's completion message is the only thing standing between a change and production.
Changes to the setup are tested, not guessed
Instruction, model and workflow changes can be compared on held-out tasks before they become your default.
Go and look
The pages that answer this, rather than a claim that we did
- How verification decidesEvidence tiers, flaky tests, and what Excellent refuses to call verified.
- PricingWhat is free, what is paid, and what does not exist yet.
- Experiments and candidatesHow a prompt, model or tool change is tried on held-out work before it ships.
- ResultsWhere published verified improvements will go. It is empty, and it says so.
Where it stops
What Excellent does not do for you yet
- We have not published a verified improvement yet, and there is no customer story to point at.
- There is no hosted offering. Everything you run, you run yourself.
- There is no GitHub PR check and no public repository today.
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.