The time went into three plumbing problems: what the action accepts as inputs, which permissions the job needs, and how the job authenticates to the model provider.
TradersPostPublished by the organization itself (post), no named author
Post: The AI Review Bot We Reverted, TradersPost blog, October 13, 2026, at Seven pull requests in one day.
Checked against the source by a first reader, then confirmed independently by a second reader who fetched the source without seeing the first reader's notes (Independent review agent (Codex, GPT-6 Astra), blind second pass from passage text and citation only, no repository access, 2026-11-07).
The complete passage matches word for word after stripping tags and collapsing whitespace, under 'Seven pull requests in one day'. It is part of Jonathan Wage's first-person account of TradersPost's work, and the surrounding context supports the supplied meaning.
TradersPost, “The AI Review Bot We Reverted”, TradersPost blog, 2026-10-13, at Seven pull requests in one day. https://blog.traderspost.io/article/the-ai-review-bot-we-built-and-reverted Archived at https://the-ai-record.com/passages/traderspost-time-went-three-plumbing-problems-2026
The builder verifies with targeted checks and runs a quick self-review. CI runs the deterministic harness. The deep review runs on request in an independent session, with the verdict returned to whoever asked. The author's watch loop handles threads and formal re-requests. Humans own the required approvals, and bot or agent verdicts do not satisfy them.
TradersPostPublished by the organization itself (post), no named author
Post: The AI Review Bot We Reverted, TradersPost blog, October 13, 2026, at What we do instead today.
We built an automated AI code review GitHub Action in a single day, and we reverted it before the day was over. The idea was simple: someone comments a trigger phrase on a pull request, and a workflow runs our deepest review and posts the result. It took seven small pull requests to get that far, and one revert pull request to undo them.
TradersPostPublished by the organization itself (post), no named author
Post: The AI Review Bot We Reverted, TradersPost blog, October 13, 2026, at Introduction.
Checks that return pass or fail belong in CI, where they are cheap and repeatable. Model judgment is reserved for what a gate cannot decide.
TradersPostPublished by the organization itself (post), no named author
Post: The AI Review Bot We Reverted, TradersPost blog, October 13, 2026, at Deterministic gates first.
Nobody wrote a postmortem. We did not collect a table of review comments the bot produced, measure their precision, or compare cost against the existing session-based review. So we cannot tell you the bot failed because of noise, or cost, or authentication friction, or a change of mind about where review should live.
TradersPostPublished by the organization itself (post), no named author
Post: The AI Review Bot We Reverted, TradersPost blog, October 13, 2026, at What we do not know.
A review bot that posts on every pull request can waste more attention than it saves. Humans have to read the comments, decide which are right, and resolve threads. A reviewer who has learned that the bot is often wrong learns to skim, and then skims the good findings too.
TradersPostPublished by the organization itself (post), no named author
Post: The AI Review Bot We Reverted, TradersPost blog, October 13, 2026, at A noisy bot costs attention.
Something wrong? Report a correction. JSON: /api/v1/passages/traderspost-time-went-three-plumbing-problems-2026.json