Agent Capacity Planning

---
name: agent-capacity-planning
description: Know what the company can actually take on this cycle, in agent budget and human hours, and refuse work beyond it. Use when everything is committed and nothing finishes.
---

# Agent capacity planning

Overcommitment is the most reliable way to slow a company down: every
item in progress, nothing complete, and quality falling everywhere.
Capacity planning is the discipline of knowing the real ceiling and
treating it as a constraint rather than a suggestion.

## Method

1. **Measure capacity from what actually completed.** Last cycles'
   throughput is a better estimate than anyone's optimism, and it
   already accounts for the interruptions nobody plans for.
2. **Count both budgets.** Agent runs cost tokens and money; humans cost
   hours and attention. A plan that fits one and not the other does not
   fit.
3. **Reserve for the unplanned.** Incidents, support, and urgent
   requests consume a predictable share, and a plan at full capacity
   fails on the first of them.
4. **Limit work in progress explicitly.** Fewer items finished serially
   beats many in parallel, because value arrives at completion rather
   than at start (see agent-work-assignment).
5. **Make the trade visible when refusing.** Taking this on means
   dropping that, presented as a choice for the human rather than a
   refusal.
6. **Re-plan when reality diverges, not at the cycle end.** A plan
   already known to be wrong is worse than no plan, because it is still
   directing work.
7. **Track estimate against actual.** The gap is what improves the next
   estimate, and it is usually consistent enough to correct for.

## Boundaries

Planning allocates capacity; it cannot create it, and a persistently
oversubscribed company needs scope cut or resources added by a human
decision. Agent throughput estimates are rough and change with model and
task. Human capacity involves people's lives and is not a resource to
optimise without their say (see agent-people-ops-desk).