ADRs or a decision log: which one a small product team needs
ADRs hold technical decisions agents must follow; a decision log holds product calls made in Slack. See them side by side, and make both agent-readable.
Blog
Notes from the team building Biddle, the AI chief of staff for product teams.
AI answers in Slack: who sees what, and why private channels stay private
How an AI assistant in Slack should scope answers to private channels, the visibility rule Biddle uses, and a checklist of questions to ask any tool first.
Daily status update template: Needs you, Since last briefing
A copyable daily status update template for product leaders: three sections in a fixed order, rules for each, a filled example and common mistakes.
Decisions lost in Slack threads: a decision log template
A decision log template for Slack: one row per decision with thread permalink, implementing PRs and superseded status, plus a one-minute capture habit.
GitHub Slack digest: events, digests and briefings compared
Your #github channel is muted. Route GitHub updates in Slack by audience: events for reviewers, a daily digest for the team, a briefing for the leader.
Keeping an AI-native product team on the same page
How to keep an AI-native product team on the same page: a shared, evidence-linked record of changes and decisions, plus a weekly rhythm you can start now.
Plan drift: when a merged PR quietly undoes a team decision
Decision drift is when merged code quietly contradicts a team decision. See how it happens and run a three-step drift check this week, no tooling needed.
Too many PRs to review? What to track when agents ship 200+ in two weeks
When agents open more PRs than anyone can read, stop tracking diffs. Track decisions, open questions and needs-a-human in a 15-minute routine.
What is an AI chief of staff for product teams?
What an AI chief of staff for product teams does, how it differs from email assistants and exec dashboards, and how to tell whether your team needs one.
Why the daily standup fails an AI-native team
Daily standup not working? Why it breaks when agents write most of the code, and how to split status from coordination, with a template to run this week.