# The Rollout Plan Document — Safe Rollout Plans for AI Features

Source: https://www.skillbyai.com/en/ai-feature-rollouts/w-plan

> Decide before you ship.

## One page, agreed in advance

A rollout plan answers, before launch: **what** is launching and for whom; **success metrics** and **guardrail metrics** with thresholds; **launch bars** (evaluation, safety, cost, latency); **stages** of exposure and how long each holds; **who decides** to advance, pause or roll back, and on what signals; the **kill switch** and fallback behaviour; **communication** to users and support; and the **owner** on call. Writing it first prevents moving goalposts under launch pressure.

## A rollout plan skeleton

Fill it in and get sign-off.

```text
feature: AI ticket summary for support agents        owner: support-ai team
success: handle time -10%; summary rated useful >= 80%
guardrails: thumbs-down <= 5%, safety flags <= 1 per 1k, p95 latency <= 5 s, cost <= $0.012/request
launch bars: eval pass >= 85% overall, >= 80% each slice; red-team blockers = 0
stages: dogfood 7d -> beta 14d -> 1% -> 5% -> 25% -> 50% -> 100% (gate checks at each)
kill switch: flag "ai-summary" (support lead + on-call can flip); fallback: last 5 messages
comms: agent training note, in-product "AI-generated" label, feedback button
rollback triggers: see monitoring section; decision makers: owner + on-call
```

## Name the decision makers

Write down who can pause or roll back without a meeting; in an incident there is no time to find out.

**Quiz:** Why write the rollout plan before launch?

- [x] To agree on metrics, bars and rollback rules before launch pressure builds
- [ ] To avoid measuring anything
- [ ] Because launches cannot be paused
- [ ] To skip user communication

*Answer:* To agree on metrics, bars and rollback rules before launch pressure builds. Decide the rules while calm.