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.
Excellent gives each run a proof trail: what was asked, what ran, what changed, what was checked. The release decision is made from evidence rather than tone.
curl -fsSL https://excellent.so/install.sh | shThe 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.
Every failed attempt teaches you something and the lesson disappears into a chat window.
You want to hand agents more of the work, but you need a release rule stronger than "the model sounded sure".
The request, the command, repo state, changed files, the checks that ran and the agent's claim land in one compact record.
A checked result can be reviewed before it lands. No agent's completion message is the only thing standing between a change and production.
Instruction, model and workflow changes can be compared on held-out tasks before they become your default.
Evidence tiers, flaky tests, and what Excellent refuses to call verified.
What is free, what is paid, and what does not exist yet.
How a prompt, model or tool change is tried on held-out work before it ships.
Where published verified improvements will go. It is empty, and it says so.
Run one real task and see what held up
curl -fsSL https://excellent.so/install.sh | sh