Segment conversion funnel drop-offs by device and marketing channel
Uncover hidden conversion bottlenecks across mobile, desktop, and paid channels. Use this when top-line conversion dips but sitewide funnels show no obvious break.
You getCritical Leaks, cross-Segment Comparison Table and diagnostic Hypotheses
Prompt
Act as a growth analytics specialist. Evaluate the multi-step conversion funnel data segmented by device and acquisition channel pasted below.
Rules:
- Calculate step-by-step conversion drop-off percentages for each device-channel combination.
- Identify the specific step where the highest absolute volume of users drops off.
- Isolate device-specific failure points that do not appear on other platforms.
- Rank the top three highest-leverage friction points based on user volume lost.
Output format:
1. Critical Leaks: Bulleted summary of the 3 largest conversion breaks by channel and device.
2. Cross-Segment Comparison Table: Columns for Step, Segment (Channel + Device), Visitors In, Drop-off Count, Step Loss Rate, Severity (High, Medium, Low).
3. Diagnostic Hypotheses: Concrete technical or UX reasons for the top anomalies observed.
4. Immediate Testing Priorities: 2 prioritized fixes or tests to run first.
My funnel data is below:Example output
Copy and paste your table of funnel steps broken down by device type and channel directly into Claude, ChatGPT or Gemini. Follow up by asking the model to estimate total visitors recovered if the top leak is halved.
Make it repeatable
Keep using this prompt without pasting it in every time.
Prompt details
- By
- Prompts-GPT editors
- Published
Did this prompt work?
Keep exploring
More like this
Estimate potential revenue recovery across funnel drop-off points
Model the financial impact of repairing conversion drop-offs across your funnel. Use this to prioritize engineering fixes by projected dollar value.
Pinpoint friction points in conversion funnels
Identify the exact bottleneck stage where prospective customers abandon your funnel. Use this when aggregate conversion drops without obvious reason.
Diagnose circular loops and friction steps in signup funnels
Map repetitive back-and-forth navigation and error loops within onboarding flows. Use this to pinpoint confusing validation rules and navigation traps.
Interpret A/B test results plainly
Turn raw conversion figures into a clear summary that non-technical stakeholders can act on without statistical jargon.
Audit driver-based models for compounding optimism bias
Expose subtle, compounding growth assumptions across pipeline stages and conversion metrics. Use this during quarterly budget reviews and board deck prep.
Clean inconsistent date formats and text categories
Turn chaotic timestamp formats and varied categorical spellings into unified standards. Use it when mismatched export values break dashboards.
- Compare cumulative customer lifetime value across monthly cohorts
- Create an anomaly investigation checklist for analytics teams
- Isolate regional or platform drivers behind KPI drops
- Resolve split device identities into single user records
- Summarize customer segment shifts for executive updates
- Translate statistical model outputs into plain business decisions