Review new agents 7-14 days after deployment — remove if actual coordination cost exceeds estimate by more than 50%

Why This Is a Rule

Every new agent added to a system was justified by an estimate: "This agent will produce X value at Y coordination cost." But estimates of coordination cost are systematically low — people underestimate the overhead of handoffs, synchronization, context-switching, and conflict resolution that a new agent introduces. The 7-14 day review provides empirical verification of the estimate against reality.

The 7-14 day window is calibrated: shorter than 7 days doesn't provide enough interaction cycles to reveal coordination patterns; longer than 14 days allows the coordination cost to become normalized ("this is just how things are now") even if it's excessive. Within this window, you can still clearly compare "before" (without the agent) to "after" (with it).

The 50% threshold is deliberately generous: if actual coordination cost exceeds the estimate by 50%, the original justification no longer holds. You estimated 2 hours/week of coordination overhead and you're spending 3+ hours — the additional hour wasn't budgeted, and the value case that justified the agent assumed the lower cost. Either redesign the agent to reduce coordination cost or remove it.

When This Fires

• 7-14 days after deploying any new behavioral agent, process step, or team member
• When a recently added agent "feels more expensive than expected" — measure rather than assume
• When the coordination budget (Cap coordination at 15-25% of total hours — new coordination mechanisms must fit within budget or displace existing ones) is being exceeded after an agent addition
• As a mandatory post-deployment gate before the new agent becomes permanent

Common Failure Mode

Skipping the review because the agent "seems to be working": the agent may be producing value while its coordination cost is quietly exceeding the budget. Value and cost must both be measured. An agent that produces $100 of value at $80 of coordination cost is a net $20 — but if the estimate was $40 of cost, the 50% overshoot (from $40 to $80) means the value case was built on wrong numbers.

The Protocol

(1) Before deploying a new agent, document the estimate: expected coordination cost per week, expected value per week. (2) Schedule a review at day 7 and day 14 post-deployment. (3) At each review, measure actual coordination cost: time spent on handoffs, synchronization, conflict resolution, context-switching, and communication related to the new agent. (4) Compare: actual cost vs. estimated cost. If actual ≤ 150% of estimate → the agent is operating within acceptable bounds. Continue. If actual > 150% of estimate → the coordination cost exceeds justification. Options: redesign the agent to reduce coordination overhead, or remove the agent entirely. (5) Document the findings for future agent additions: what coordination costs were underestimated? This improves future estimates.