Product Analytics Insights

Objective: Equip product managers and analysts with a modular AI prompt that converts raw event data, funnels, and cohort metrics into prioritized, evidence-based recommendations without requiring advanced statistical expertise.

The base prompt was formed by following these steps:

Identify the core need: transform scattered product metrics into decisions that improve retention, activation, or monetization.
Separate fixed guidance (analysis method, output structure, quality rules) from changeable inputs (product context, specific metrics, time window).
Encode the fixed guidance as reusable snippets so the same analytical rigor can be applied across products.
Isolate the changeable inputs as variables so the prompt stays short and easy to update.
Add explicit constraints on evidence and prioritization to reduce hallucinated insights.
Require a consistent output format so results can be shared directly in roadmaps or sprint planning.

Note

Keep the prompt focused on one primary goal per run (for example retention or conversion). Mixing too many goals dilutes the quality of recommendations.

Prompt Template

You are a senior product analyst. Analyze the following product analytics data for {{product_name}} covering {{time_period}}.

{{snippet:analysis_framework}}

Focus on these metrics: {{key_metrics}}.
User segment of interest: {{user_segment}}.
Business goal: {{primary_goal}}.

{{snippet:output_structure}}

{{snippet:quality_rules}}

Respond in {{tone}}.

Element	Type	Example value
{{product_name}}	variable	Mobile banking app
{{time_period}}	variable	Last 90 days
{{key_metrics}}	variable	Activation rate, Day-7 retention, Feature adoption of bill pay
{{user_segment}}	variable	New users who completed KYC
{{primary_goal}}	variable	Increase Day-7 retention by 15%
{{tone}}	variable	Concise and data-driven
{{snippet:analysis_framework}}	snippet	Apply cohort analysis, funnel drop-off inspection, and correlation checks between feature usage and retention. Highlight statistical significance only when sample size exceeds 1,000 users.
{{snippet:output_structure}}	snippet	Structure the response as: 1. Key findings (3-5 bullets with numbers), 2. Root-cause hypotheses ranked by impact, 3. Recommended experiments with expected lift and effort, 4. Suggested next metrics to track.
{{snippet:quality_rules}}	snippet	Base every claim on the provided data. Do not invent numbers. Flag any data gaps. Rank recommendations by estimated impact versus implementation effort.

Prompt Example

You are a senior product analyst. Analyze the following product analytics data for Mobile banking app covering Last 90 days.

Apply cohort analysis, funnel drop-off inspection, and correlation checks between feature usage and retention. Highlight statistical significance only when sample size exceeds 1,000 users.

Focus on these metrics: Activation rate, Day-7 retention, Feature adoption of bill pay.
User segment of interest: New users who completed KYC.
Business goal: Increase Day-7 retention by 15%.

Structure the response as: 1. Key findings (3-5 bullets with numbers), 2. Root-cause hypotheses ranked by impact, 3. Recommended experiments with expected lift and effort, 4. Suggested next metrics to track.

Base every claim on the provided data. Do not invent numbers. Flag any data gaps. Rank recommendations by estimated impact versus implementation effort.

Respond in Concise and data-driven.

Tip

After the first run, feed the AI the actual tables or event summaries from your analytics tool. The more concrete the numbers, the sharper the prioritization becomes.

Extended example values:

{{product_name}}
- Mobile banking app
- B2B SaaS project management platform
- Consumer fitness wearable companion app
{{time_period}}
- Last 90 days
- Q2 2026
- 30 days post-feature launch
{{key_metrics}}
- Activation rate, Day-7 retention, Feature adoption of bill pay
- Free-to-paid conversion, Weekly active users, Time-to-first-value
- Session length, Churn rate, Push notification open rate
{{user_segment}}
- New users who completed KYC
- Power users with 10+ projects
- Users aged 25-34 who enabled health goals
{{primary_goal}}
- Increase Day-7 retention by 15%
- Raise free-to-paid conversion from 4% to 7%
- Reduce 30-day churn by 10 percentage points
{{tone}}
- Concise and data-driven
- Collaborative and action-oriented
- Executive summary style
{{snippet:analysis_framework}}
- Apply cohort analysis, funnel drop-off inspection, and correlation checks between feature usage and retention. Highlight statistical significance only when sample size exceeds 1,000 users.
- Use retention curves, feature engagement scoring, and segmentation by acquisition channel. Surface only patterns that hold across at least two consecutive cohorts.
{{snippet:output_structure}}
- Structure the response as: 1. Key findings (3-5 bullets with numbers), 2. Root-cause hypotheses ranked by impact, 3. Recommended experiments with expected lift and effort, 4. Suggested next metrics to track.
- Deliver: Executive summary (max 80 words), Detailed findings table, Prioritized experiment backlog with owner suggestions, Risks and open questions.
{{snippet:quality_rules}}
- Base every claim on the provided data. Do not invent numbers. Flag any data gaps. Rank recommendations by estimated impact versus implementation effort.
- Cite exact metric values and sample sizes. Separate correlation from causation. Limit recommendations to three high-confidence experiments.