Use This Doc For
/platform/ai/platform/ai/capacity-continuity/platform/ai/operations/platform/ai/operations-map/platform/ai/capability-needs/platform/ai/history/platform/ai/assignments — Priority & Models: the everyday Cost / Quality / Time priority (platform default) and the advanced per-coworker guardrails on one surface (/platform/ai/priority redirects here)
Workflow
- Start with the current operating picture: health, recent activity, operations-map posture, and assignment posture.
- Review Capacity Continuity when paid AI capacity is idle, blocked, or expected to keep working during holidays, vacations, business events, after-hours windows, or owner inactivity.
- Review Capability Needs when coworkers surface missing tools, prompts, permissions, or product gaps that need governed follow-up.
- Review history when a result looks wrong, slow, or inconsistent.
- Adjust Priority & Models only after you understand whether the problem is role design, model selection, tool access, standing orders, or calendar state. Set the everyday Cost / Quality / Time priority at the top of that surface (or per coworker from the triangle at its composer); reserve the advanced guardrails below — a tier floor, a pinned model — for hard limits the priority must not cross.
What To Watch
- work being routed to the wrong specialist
- paid AI capacity going unused without a clear blocker
- repeated retries or stalled history patterns
- assignment changes that solve one route but weaken another
- capacity work that produces token spend without durable evidence, backlog movement, or reviewable output
- capability needs without submitter context, route context, or a clear backlog follow-up
Edit this page on GitHub
