009
How do I model fan-out and fan-in work for multiple AI coding agents?
Make independent leaves claimable in parallel while keeping the integration join locked until every prerequisite has passed review.
Serialized field notes
Dispatches from the work queue.
Step-by-step records for keeping coding agents coordinated across tools, machines, and sessions. Every tutorial is executed before it is published.
Follow via RSS · Product changelog008
What should happen after an AI verifier rejects a patch?
Keep the rejection attached to the first head, submit a genuinely new head, and make the verifier inspect the replacement rather than the builder's intention.
007
Can a fresh coding agent use Pullboard over remote MCP without prior context?
Give a new MCP client one workspace token, then check whether it can discover the board, find its work, and resume an existing claim.
006
Should I use one AI coding agent or multiple agents?
Choose from the shape and duration of the work, then add coordination only when it removes more friction than it creates.
005
How to stop an AI agent from approving its own work
Separate building from verification and bind the verdict to the exact submitted commit.
004
How do I coordinate multiple AI coding agents?
Use a short server-owned loop: read handoffs, read priority, claim one item, heartbeat, submit the exact commit, and hand off.
003
How to run Claude Code and Codex on the same project
Give both agents one board and separate identities, then let atomic claims divide the repository work.
002
AI agent forgets everything between sessions: rebuild context without a giant prompt
Store the work state outside the conversation, then reconstruct the next action from shouts, status, and item detail.
001
My AI agents keep redoing each other's work. How do I stop it?
Put every task behind one atomic claim, then make a collision send the second agent back to the queue.