KPI Analysis
KPI Review for a Weekly Meeting
Turn a stack of metrics into a one-page weekly: what moved, why it might have, and what to do.
The Prompt
kpi-review-for-a-weekly-meeting.md
Write a weekly KPI review. Period: {{period}} Metrics (name, this period, last period, target if any): {{metrics}} Known events (launches, outages, seasonality): {{events}} Audience: {{audience}} One page: 1. Headline: the one number that matters this week 2. Table: metric / now / delta / vs target / one-line comment 3. 3 hypotheses for the biggest move - labelled as hypothesis, not fact 4. 3 actions (owner placeholders if I did not name people) 5. What to ignore (noise, vanity) Do not invent causes that are not in {{events}} or the numbers. If data is incomplete, lead with that.
Negative prompt
Included when you copy the prompt
Do not invent causes beyond {{events}} and the metric deltas. Do not present hypotheses as proven facts. Do not pad with vanity metrics or equal weight on every line. Do not write a multi-page essay - keep it one page. Do not invent owners, targets, or events that were not provided. If metrics are incomplete, lead with that instead of a confident narrative.
Fill in your details below - this prompt updates as you type, then copy it.
Fill in your details
0 of 4 filled. Preview updates as you type - then copy the finished prompt (negative prompt included when present).
kpi-review-for-a-weekly-meeting.md
Prompt preview
Write a weekly KPI review. Period: {{period}} Metrics (name, this period, last period, target if any): {{metrics}} Known events (launches, outages, seasonality): {{events}} Audience: {{audience}} One page: 1. Headline: the one number that matters this week 2. Table: metric / now / delta / vs target / one-line comment 3. 3 hypotheses for the biggest move - labelled as hypothesis, not fact 4. 3 actions (owner placeholders if I did not name people) 5. What to ignore (noise, vanity) Do not invent causes that are not in {{events}} or the numbers. If data is incomplete, lead with that.
Examples
Example input
Period: Week of 2026-08-11 Metrics: Activation rate: 28% (was 31%, target 30%) Weekly active users: 12,400 (was 11,900, target 12,000) Paid conversion: 3.1% (was 3.0%, target 3.5%) Support tickets / 100 users: 4.8 (was 3.2, no target) NPS sample: n=40, score 32 (was 38) Known events: New onboarding checklist shipped Tue; 90-min API outage Thu afternoon; back-to-school promo live all week Audience: leadership
What you should get
1. Headline: Activation fell 3pp to 28% (below 30% target) in the same week we shipped new onboarding and had a Thu outage. 2. Table: WAU +500 vs last week / above target - healthy top of funnel. Activation 28% / −3pp / miss - primary concern. Paid conversion +0.1pp / still below target. Tickets +1.6 - watch. NPS drop on n=40 - treat as noisy. 3. Hypotheses (not facts): (H1) New checklist added friction for first-run users. (H2) Thu outage truncated sessions mid-activation. (H3) Promo mixed in lower-intent traffic that activates less. 4. Actions: Owner TBD - funnel drop-off by onboarding step for pre/post Tue. Owner TBD - quantify activation among users active during the outage window. Owner TBD - segment activation promo vs non-promo. 5. Ignore: NPS until n>200; raw ticket volume without severity; celebrating WAU alone while activation misses.
When to use this prompt
Use it when
- You need help with pms.
- You need help with founders.
- You need help with ops.
Skip it when
- You only need a one-line ask with no constraints, format, or context.
- You cannot supply the fill-in details the template asks for.
- A different category or tool-specific workflow fits the job better.
How to get a good result
Done when
1. Headline: Activation fell 3pp to 28% (below 30% target) in the same week we shipped new onboarding and had a Thu outage. 2. Table: WAU +500 vs last week / above target - healthy top of funnel. Activation 28% / −3pp / miss - primary concern. Paid conversion +0.1pp / still below target. Tickets +1.6 - watch. NPS drop on n=40 - treat as noisy. 3. Hypotheses (not facts): (H1) New checklist added friction for first-run users. (H2) Thu outage truncated sessions mid-activation. (H3) Promo mixed in lower-intent traffic that activates less. 4. Actions: Owner TBD - funnel drop-off by onboarding step for pre/post Tue. Owner TBD - quantify activation among users active during the outage window. Owner TBD - segment activation promo vs non-promo. 5. Ignore: NPS until n>200; raw ticket volume without severity; celebrating WAU alone while activation misses.
Common mistakes
- Leaving period, metrics, events vague - the model then invents placeholders.
- Asking ChatGPT, Claude, or Gemini for a shorter answer after a long structured prompt - that throws away the format rules.
- Stopping when the first draft appears instead of checking it against the success criteria below.
FAQ
- What do I fill in before I copy this prompt?
- Replace these placeholders with your details: period, metrics, events, audience. Required fields are marked on the page. The prompt text updates as you type.
- Which AI tools is this prompt written for?
- It works best with ChatGPT, Claude, Gemini. Copy the filled prompt and paste it into the tool you already use.
- What should a good result look like?
- 1. Headline: Activation fell 3pp to 28% (below 30% target) in the same week we shipped new onboarding and had a Thu outage. 2. Table: WAU +500 vs last week / above target - healthy top of funnel. Activation 28% / −3pp / miss - primary concern. Paid conversion +0.1pp / still below target. Tickets +1.6 - watch. NPS drop on n=40 - treat as noisy. 3. Hypotheses (not facts): (H1) New checklist added friction for first-run users. (H2) Thu outage truncated sessions mid-activation. (H3) Promo mixed i…
- What are common mistakes with this prompt?
- Leaving period, metrics, events vague - the model then invents placeholders. Asking ChatGPT, Claude, or Gemini for a shorter answer after a long structured prompt - that throws away the format rules. Stopping when the first draft appears instead of checking it against the success criteria below.
Best for
- PMs
- Founders
- Ops
Related Prompts
More prompts like this — same topic and style.
