Your team agrees on something in Slack. Two weeks later a PR quietly breaks it. Nobody catches it until QA — or after deploy. Mo watches a Slack channel for decisions. When someone tags @mo to approve something, it stores it. When a PR opens, Mo checks the diff against every approved decision and flags conflicts before merge. It doesn't review code quality. It only cares if the code matches what the team actually decided.
We built this after it happened to us — a decision made in Slack
didn't make it into the code, and nobody caught it until a customer
hit it in production.
The frustrating part wasn't the bug. It was that the decision was
right there in #product-decisions. The PR just never got checked
against it.
Mo is the connection that was missing. Happy to answer any questions
about how the decision matching works under the hood.
The @mo to approve mechanic is clever. Lightweight enough that teams might actually adopt it without resistance.
Interesting approach. Curious how this handles the agent pipeline - when an AI agent opens the PR, does it still catch conflicts with decisions made before the agent was involved? The drift window starts earlier than that.
How do you decide which Slack discussions actually become enforceable rules without creating noise?
