name: measure-experiment-results
description: Documents the results of a completed experiment or A/B test with statistical analysis, learnings, and recommendations. Use after experiments conclude to communicate findings, inform decisions, and build organizational knowledge.
phase: measure
version: "2.0.0"
updated: 2026-01-26
license: Apache-2.0
metadata:
category: reflection
frameworks: [triple-diamond, lean-startup, design-thinking]
author: product-on-purpose
Experiment Results
An experiment results document captures what happened when you tested a hypothesis, including statistical outcomes, segment analysis, learnings, and clear recommendations. Good results documentation turns individual experiments into organizational knowledge that improves future decision-making.
When to Use
- After an A/B test or experiment reaches statistical significance
- When an experiment is ended early (for any reason)
- To communicate findings to stakeholders who weren't involved
- During decision-making about whether to ship, iterate, or kill a feature
- To build a repository of learnings that inform future experiments
Instructions
When asked to document experiment results, follow these steps:
Summarize the Experiment
Provide context: what was tested, when it ran, how much traffic it received. Link to the original experiment design document if one exists.
Restate the Hypothesis
Remind readers what you believed would happen and why. This frames the results interpretation.
Present Primary Results
Show the primary metric outcome clearly: what were the values for control and treatment? Include statistical significance (p-value), confidence intervals, and sample sizes. Be honest about whether results are conclusive.
Analyze Secondary Metrics
Present guardrail metrics that ensure you didn't cause unintended harm. Note any secondary metrics that moved unexpectedly—both positive and negative.
Segment the Data
Look for differential effects across user segments (platform, tenure, plan type, etc.). Sometimes overall results mask important segment-level insights.
Extract Learnings
What did you learn beyond the numbers? Include surprising findings, questions raised, and implications for the product hypothesis. Negative results are valuable learnings.
Make a Recommendation
Be clear: should we ship, iterate, or kill? Support the recommendation with the evidence. If the decision is nuanced, explain the trade-offs.
Define Next Steps
Specify what happens now—engineering work to ship, follow-up experiments, metrics to continue monitoring, or documentation to update.
Output Format
Use the template in references/TEMPLATE.md to structure the output.
Quality Checklist
Before finalizing, verify:
Examples
See references/EXAMPLE.md for a completed example.
1---2name: measure-experiment-results3description: <!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->4---5
6<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->
7---
8name: measure-experiment-results
9description: Documents the results of a completed experiment or A/B test with statistical analysis, learnings, and recommendations. Use after experiments conclude to communicate findings, inform decisions, and build organizational knowledge.
10phase: measure
11version: "2.0.0"
12updated: 2026-01-26
13license: Apache-2.0
14metadata:
15 category: reflection
16 frameworks: [triple-diamond, lean-startup, design-thinking]
17 author: product-on-purpose
18---
19# Experiment Results
20
21An experiment results document captures what happened when you tested a hypothesis, including statistical outcomes, segment analysis, learnings, and clear recommendations. Good results documentation turns individual experiments into organizational knowledge that improves future decision-making.
22
23## When to Use
24
25- After an A/B test or experiment reaches statistical significance
26- When an experiment is ended early (for any reason)
27- To communicate findings to stakeholders who weren't involved
28- During decision-making about whether to ship, iterate, or kill a feature
29- To build a repository of learnings that inform future experiments
30
31## Instructions
32
33When asked to document experiment results, follow these steps:
34
351. **Summarize the Experiment**
36 Provide context: what was tested, when it ran, how much traffic it received. Link to the original experiment design document if one exists.
37
382. **Restate the Hypothesis**
39 Remind readers what you believed would happen and why. This frames the results interpretation.
40
413. **Present Primary Results**
42 Show the primary metric outcome clearly: what were the values for control and treatment? Include statistical significance (p-value), confidence intervals, and sample sizes. Be honest about whether results are conclusive.
43
444. **Analyze Secondary Metrics**
45 Present guardrail metrics that ensure you didn't cause unintended harm. Note any secondary metrics that moved unexpectedly—both positive and negative.
46
475. **Segment the Data**
48 Look for differential effects across user segments (platform, tenure, plan type, etc.). Sometimes overall results mask important segment-level insights.
49
506. **Extract Learnings**
51 What did you learn beyond the numbers? Include surprising findings, questions raised, and implications for the product hypothesis. Negative results are valuable learnings.
52
537. **Make a Recommendation**
54 Be clear: should we ship, iterate, or kill? Support the recommendation with the evidence. If the decision is nuanced, explain the trade-offs.
55
568. **Define Next Steps**
57 Specify what happens now—engineering work to ship, follow-up experiments, metrics to continue monitoring, or documentation to update.
58
59## Output Format
60
61Use the template in `references/TEMPLATE.md` to structure the output.
62
63## Quality Checklist
64
65Before finalizing, verify:
66
67- [ ] Statistical methods and significance are clearly stated
68- [ ] Confidence intervals are included (not just p-values)
69- [ ] Segment analysis checked for differential effects
70- [ ] Secondary/guardrail metrics are reported
71- [ ] Learnings go beyond just the numbers
72- [ ] Recommendation is clear and actionable
73- [ ] Negative or inconclusive results are reported honestly
74
75## Examples
76
77See `references/EXAMPLE.md` for a completed example.
majiayu000