collabd gives one answer on every pull request — safe to ship, needs your review, or do not ship — whoever or whatever wrote it, bound to the exact commit it judged.
There is no fourth state. When the reviewer cannot reach a judgement at all you get a slate ◎ and the reason — never a colour collabd has not earned.
The reviewer is a separate context from whatever wrote the code, so it has nothing invested in the answer.
Three states and only three. No percentage, no risk number, nothing to interpret.
Every finding is pinned to the exact file and line that produced it, worst first.
Approve a plan with acceptance criteria and the verdict grades the diff against them — on the work collabd authors.
Bound to the exact commit. Move the code and it goes stale rather than lying to you.
Export the immutable, secret-redacted bundle behind any verdict. It reads fine without us.
Who approved, who overrode, who shipped, and what they wrote. Overriding is allowed, and recorded.
Once before anything is written, once before anything ships. Everything between those two moments is the agent’s problem, not yours.
One sentence. Or let collabd read the repo and propose something itself.
Steps, files, open questions. Nothing is written until you say yes.
Sandboxed, on a branch, with its own tests. Never on your default branch.
The verdict lands and you decide. collabd never merges on its own judgement.
Same reviewer, same three answers, on every pull request your team opens — whoever or whatever wrote it.
One authors on a branch and opens pull requests. One only reads. Neither merges on its own judgement — a human clicks Ship.
Builds and reviews cannot reach your credentials or your infrastructure.
Check summaries, evidence bundles and the audit trail are scrubbed before they leave.
Closed beta, with people already running several agents and losing track of what is safe to merge.