Kiro Crew Ultra Mode splits big jobs across AI chats and manages them on one screen(zenn.dev)
Writing language: KoreanRead in the original language
Plain summary
- Ultra Mode in the open-source tool Kiro Crew splits a single goal into multiple tasks, assigns each to a separate AI chat, and brings progress and approval requests together on one board.
- A conductor AI sets completion criteria for each task and writes them in a ledger (task log). Task AIs only report results and cannot change their own completion criteria or mark themselves as passed. Records remain after a restart.
- It arrived as a feature preview in 0.12.0 and is off by default. By default, each task assignment requires approval, and the default number of tasks opened simultaneously per goal is 6. The author derived this figure by reading the code.
- In the author's server inspection test, approval was required to assign tasks, run commands, check completion criteria, and close chats. When a task AI reports that it is finished, the board shows it as complete, but the ledger entry remains open until the conductor AI checks and closes it.
Editorial opinion
O: If you're the operations person in charge of server checks, it's worth testing the approval flow first with two small read-only tasks, such as checking disk usage and checking for failed systemd services.
X: When a worker AI reports done, the board shows the task as complete, but the ledger stays open until the conductor checks the completion conditions and closes it, so you shouldn't trust the completion mark alone.
Writing language: Korean
Found on
Zenn ↗ / Published by source
Have you run into something like this? Tell us in a line or two what you did. You do not need to know the product.