The A/B Test Interpreter: Ship, Hold, or Kill in One Prompt
Why this prompt matters
Bad ship/kill calls are expensive in both directions. Shipping a false positive locks in code that looks like a winner in the dashboard but quietly erodes revenue for months before anyone traces it back to the test. Killing a real winner because the raw numbers looked shaky under-delivers growth you already earned. And teams that 'peek' at results early and stop tests as soon as the trend looks good introduce a well-documented bias that inflates the apparent win rate of every experiment program — this prompt forces a power and significance check before any of that can happen.
What we use it for
You're a growth PM and your two-week checkout redesign A/B test just wrapped. Leadership wants a ship/no-ship call in tomorrow's roadmap review, but the raw dashboard just shows a conversion rate that went up — it doesn't tell you if that's a real 5% lift or noise that will vanish next month, and nobody on the team has time to run the statistics by hand before the meeting.
Prompt
Act as a senior product analyst and growth data scientist with deep expertise in experimental design and statistical inference for digital products. CONTEXT: I ran an A/B test with the following setup: - Test name / hypothesis: [TEST NAME/HYPOTHESIS] - Primary success metric: [PRIMARY SUCCESS METRIC] - Control group result: [CONTROL METRIC AND VALUE] - Variant group result: [VARIANT METRIC AND VALUE] - Sample sizes: [SAMPLE SIZES] (control vs. variant) - Test duration: [TEST DURATION] - Guardrail metrics tracked (if any): [GUARDRAIL METRICS, IF ANY] - Any other context (traffic source, platform, seasonality, known anomalies): [ADDITIONAL CONTEXT] TASK: Analyze this experiment and produce a ship/hold/kill recommendation. Your analysis must: 1. Calculate or estimate statistical significance (p-value or confidence interval) for the primary metric given the sample sizes provided. 2. Assess statistical power — flag explicitly if the sample size is too small to trust the result either way. 3. Distinguish statistical significance from practical/business significance — a "significant" result that moves the needle by a trivial amount is not a reason to ship. 4. Check the guardrail metrics for regressions, even if the primary metric looks like a win. 5. Give a clear final recommendation: SHIP, HOLD (extend test), or KILL — with your reasoning stated in plain terms a non-technical stakeholder can follow. CONSTRAINTS: - Do NOT recommend shipping on a result that is underpowered — say so explicitly and recommend the minimum additional sample size or duration needed instead. - Explicitly flag possible novelty effects if the test ran less than 2 full business cycles (e.g., under 2 weeks for a weekly-cadence product). - Explicitly flag risk of "peeking" bias if the numbers suggest the test may have been stopped early based on interim results. - Never conflate correlation from a single test with certainty — mention confounding variables if the context suggests any (seasonality, traffic mix changes, etc.). - Keep the tone direct and decision-oriented — this is going into a roadmap review, not a stats textbook. OUTPUT FORMAT: ## Statistical Read [Confidence interval / p-value, power assessment, in plain language] ## Business Interpretation [What this actually means for the product and the metric that matters] ## Recommendation: [SHIP / HOLD / KILL] [2-3 sentence justification] ## Caveats & Follow-Up [1-2 risks or suggested follow-up tests]
Result
Scenario: Checkout flow redesign test, e-commerce site, 14-day run.
Statistical Read
Control: 4.8% conversion (n=24,600 sessions). Variant: 5.05% conversion (n=24,450 sessions). That's a +5.2% relative lift. Running a two-proportion z-test on these numbers gives a p-value of approximately 0.041 — just inside the conventional 0.05 significance threshold, with a 95% confidence interval on the lift of roughly [+0.1%, +10.3%] relative. Post-hoc power at this effect size and sample size lands around 52%, well below the 80% threshold you'd want for a decision this consequential. In plain terms: the result is nominally significant, but the confidence interval is wide enough that the "true" lift could be barely above zero or as high as 10% — you don't have enough data to know which.
Business Interpretation
A +5.2% relative lift on checkout conversion is commercially meaningful if real — at your traffic volume that's roughly 60 incremental orders per day. But the wide confidence interval means you're not choosing between "ship" and "don't ship," you're choosing between "possibly a strong winner" and "possibly noise." The guardrail metric (average order value) held flat at -0.3% (not significant), so there's no evidence the variant is cannibalizing basket size to win on conversion rate. No red flags there.
Recommendation: HOLD
Extend the test by at least 7-10 more days to reach ~80% power at the observed effect size (approximately 34,000 sessions per arm). The 14-day window also only covers two weekly cycles, borderline for ruling out a novelty effect on a redesigned flow — extending the window addresses both the power problem and the novelty-effect risk simultaneously. Shipping now on a 52%-powered result risks locking in a false positive that erodes checkout conversion once the novelty wears off.
Caveats & Follow-Up
Check whether the lift is concentrated in mobile vs. desktop traffic — redesigns often show device-specific effects that average out misleadingly. Also confirm the test wasn't peeked at and stopped early; if the 14-day window was chosen after seeing early results trending positive, treat this read with additional skepticism and weight the extension recommendation even more heavily.
Most teams read an A/B test result the same way: control number, variant number, whichever is higher wins. That's how false positives get shipped and how real winners get killed by nervous stakeholders who see a small sample and get spooked. This prompt exists to force five checks that a dashboard glance skips — significance, power, practical significance, guardrail regressions, and bias risks like novelty effects and early peeking — before anyone commits to a ship/hold/kill call.
Why the structure works
The Context section deliberately asks for sample sizes and test duration up front, not just the headline metrics. Significance and power calculations are meaningless without them, and it's exactly the information most people leave out when they paste "control was 4.8%, variant was 5.05%" into a chat window expecting a verdict.
The Constraints section is where the real value lives. Explicitly banning a "ship" recommendation on an underpowered result stops the most common failure mode: a test that reached nominal significance (p just under 0.05) but was never run long enough to reach a trustworthy sample size. The novelty-effect flag catches redesigns and UI changes that spike a metric temporarily because users are reacting to something new, not because the change is actually better — a distinction that only shows up if the test runs long enough to cover multiple full usage cycles. The peeking-bias flag addresses a well-known statistical trap: teams that check results daily and stop the test the moment it looks good are effectively running dozens of hidden hypothesis tests, which inflates the false-positive rate far above the nominal 5%.
The Output Format separates "Statistical Read" from "Business Interpretation" on purpose. A p-value of 0.03 means nothing to a VP in a roadmap review — but "there's a real chance this lift is close to zero" does. Splitting the two forces the model to translate the stats into a decision-usable sentence instead of stopping at the number.
How to use it well
Fill in the bracketed fields directly from your experimentation platform's export — don't round the numbers by hand, since the power calculation depends on the actual sample sizes. If you don't have a formal guardrail metric defined, put "none tracked" rather than leaving it blank — that gap is itself worth flagging in the output, since shipping on a single metric with no downside checks is its own risk.