For engineering teams
One rule for trusting agent work, across a team of twenty to fifty
Different engineers use different agents and the review burden lands in the same place. Excellent gives every agent run the same shape — attempt, checks, evidence, result — so reviewers compare records instead of arguing from transcripts.
The problems
Three things engineering teams keep telling us
01
One engineer trusts a passing unit test, another wants browser evidence, and nobody can say what the agent actually observed.
02
Agent runs happen in local terminals, pull requests and CI logs, and the evidence is scattered across all three.
03
A regression gets through because the reviewer had to reconstruct the context after the fact.
Outcomes
What verified agent work looks like for you
One result vocabulary
Every run ends verified, returned or unchecked, with the same fields behind each word — so a review conversation starts from the same facts.
Evidence stays attached to the attempt
Repo state, command output, test results and reviewer notes belong to the run that produced them, not to whoever remembers them.
No self-approval
The worker's completion claim is kept separate from the evidence that decides whether the work moves forward.
Go and look
The pages that answer this, rather than a claim that we did
- Checks and resultsWhat a check is, and what each result state commits to.
- Work and attemptsThe record shape a reviewer reads, including retries.
- TeamsWhat running Excellent across a team looks like today, and what it costs.
- Security and dataWhere attempts, artifacts and receipts are written, and what leaves the machine.
Where it stops
What Excellent does not do for you yet
- Verification evidence does not sync between teammates yet. Receipts stay on the machine that produced them.
- There is no hosted service, no SSO and no invite flow.
- macOS only. Windows and Linux support is not scheduled.
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.