growth-experiment-planner
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseGrowth Experiment Planner
增长实验规划工具
When to invoke
调用场景
- "Plan an A/B test for the new onboarding flow."
- "How long do we need to run this experiment?"
- "Draft an experiment brief for the pricing page test."
- "为新用户引导流程规划A/B测试。"
- "这个实验需要运行多久?"
- "为定价页面测试草拟实验简报。"
Inputs needed
所需输入
- Hypothesis — what change, expected effect, why.
- Primary metric — name, baseline rate or mean, variance if known.
- Traffic — daily users hitting the surface.
- MDE — minimum detectable effect (relative).
- Variants — control + N treatments.
- Guardrails — metrics that must NOT regress (revenue, errors, latency).
- 假设 — 要做出的变更、预期效果及原因。
- 核心指标 — 名称、基准转化率或均值,若已知则提供方差。
- 流量 — 每日访问该页面的用户数量。
- MDE — 最小可检测效果(相对值)。
- 变体 — 对照组 + N个实验组。
- 防护指标 — 不得出现退化的指标(收入、错误率、延迟)。
Workflow
工作流程
- Frame — restate hypothesis in one sentence.
- Size — call to compute sample size and runtime.
plan.py - Spec — generate experiment brief: metrics, segments, allocation, stopping rules, guardrails.
- Checklist — pre-launch QA, holdout, instrumentation, rollback path.
- Hand off — output a Markdown brief ready for LaunchDarkly/Optimizely.
- 梳理 — 用一句话重述假设。
- 确定规模 — 调用计算样本量和运行时长。
plan.py - 制定规范 — 生成实验简报:指标、用户细分、流量分配、停止规则、防护指标。
- 检查清单 — 启动前QA、对照组留存、埋点验证、回滚路径。
- 交付 — 输出可直接用于LaunchDarkly/Optimizely的Markdown格式简报。
Output format
输出格式
A complete experiment brief with: Hypothesis, Variants, Metrics, Sample size, Runtime, Allocation, Guardrails, Stopping rules, QA checklist, Rollback plan.
一份完整的实验简报,包含:假设、变体、指标、样本量、运行时长、流量分配、防护指标、停止规则、QA检查清单、回滚方案。
Guardrails
防护规则
- Always require a primary metric defined before launch (no metric fishing).
- Require explicit guardrails — at minimum: error rate, p95 latency, revenue per user.
- Flag if runtime exceeds 4 weeks (novelty + seasonality risk).
- 启动前必须明确核心指标(禁止事后找指标)。
- 必须明确防护指标 — 至少包括:错误率、p95延迟、单用户收入。
- 若运行时长超过4周则标记风险(新奇效应+季节性风险)。
Reference code
参考代码
plan.pyplan.py