Delegation down the chain with fan-out

The idea

A manager splits work into parts, creates every child in one transaction with dependencies, and waits once for all of them.

The problem
One child per round is slow and loses dependency order.
Why it matters
Independent parts run in parallel and the parent resumes when all are done.
Where it stands
In production as of

A step-by-step replay of this idea is not published yet. The library adds one when a recorded run shows it.

  • CEO front door over a worker hierarchy

    The operator talks to one CEO worker; department heads and workers sit below it, and each level's budget and tool limits bind its whole subtree.

  • Parallel work in one repository by footprint

    Each plan predicts the files and functions it touches; overlapping work goes to the same worker or waits, and disjoint work runs side by side without worktrees.

  • Define deeply before building

    Before building, the worker defines what, why, for whom and how. It checks fit, knowledge and authority, and answers its own questions with research and with colleagues.

Turn the numbers into shipped work.

Crewshal runs these choices for you: a persistent AI worker with memory and rules, on your Claude and Codex subscriptions.