Funnel Drop-Off Analysis Prompt
Diagnose where and why users drop off in your conversion funnel, with data interpretation frameworks, hypothesis generation, and prioritized experiment recommendations.
Prompt Template
I have a [type of funnel, e.g., SaaS signup, e-commerce checkout, onboarding] funnel with the following stages and conversion data: [Paste your funnel data, e.g.: - Landing page visits: [number] - Signup started: [number] - Email verified: [number] - Onboarding step 1 completed: [number] - Onboarding step 2 completed: [number] - First value action (e.g., created first project): [number] - Converted to paid: [number]] Additional context: - Industry: [industry] - Traffic source mix: [e.g., 40% organic, 30% paid ads, 20% referral, 10% direct] - Time period: [date range] - Any recent changes: [e.g., redesigned signup page, changed pricing] Please provide: 1. **Funnel Visualization**: Show stage-by-stage conversion rates and cumulative drop-off 2. **Benchmark Comparison**: Compare my rates to typical [industry] benchmarks and flag stages that are significantly below average 3. **Drop-Off Diagnosis**: For each major drop-off point: - Likely root causes (list 3-5 hypotheses) - Data you'd want to investigate further - Quick wins vs. structural fixes 4. **Prioritized Experiment Plan**: Recommend 5 experiments ranked by expected impact and effort (use an ICE framework: Impact, Confidence, Ease) 5. **Tracking Gaps**: Identify what additional events or data points I should be tracking to better understand the funnel
Example Output
# Funnel Drop-Off Analysis: SaaS Onboarding Funnel
Period: Jan 1 – Feb 28, 2026
1. Funnel Visualization
Landing Page ████████████████████████████ 10,000 (100%)
Signup Started ██████████████████ 6,200 (62.0%) ← 38% drop
Email Verified █████████████ 4,960 (49.6%) ← 20% drop
Onboard Step 1 ██████████ 3,720 (37.2%) ← 25% drop
Onboard Step 2 ████████ 2,604 (26.0%) ← 30% drop ⚠️
First Project █████ 1,562 (15.6%) ← 40% drop 🔴
Paid Conversion ██ 625 (6.3%) ← 60% drop 🔴
**Overall funnel conversion: 6.3%** (Landing → Paid)
2. Benchmark Comparison
| Stage | Your Rate | B2B SaaS Benchmark | Status |
|-------|-----------|-------------------|--------|
| Visit → Signup | 62% | 40-60% | ✅ Above average |
| Signup → Verified | 80% | 75-85% | ✅ On track |
| Verified → Onboard 1 | 75% | 70-80% | ✅ On track |
| Onboard 1 → 2 | 70% | 80-90% | ⚠️ Below average |
| Onboard 2 → First Value | 60% | 70-80% | 🔴 Significantly below |
| First Value → Paid | 40% | 15-30% | ✅ Strong |
3. Drop-Off Diagnosis
🔴 Critical: Onboard Step 2 → First Project (40% drop)
Hypotheses:
1. Users don't understand what "first project" means or why they should create one
2. The project creation flow has too many required fields
3. Users who completed onboarding steps aren't the right ICP
4. No in-app guidance or templates to reduce blank-page anxiety
5. Time-to-value is too long — users abandon before experiencing the "aha moment"
**Investigate:** Session recordings, time-on-step data, user role/company size segments
**Quick win:** Add pre-built templates so users can start with one click
**Structural fix:** Redesign onboarding to include project creation within the flow
4. Prioritized Experiments (ICE Framework)
| # | Experiment | Impact | Confidence | Ease | ICE Score |
|---|-----------|--------|------------|------|----------|
| 1 | Add "Start from template" on first project screen | 9 | 8 | 9 | 8.7 |
| 2 | Reduce onboarding Step 2 fields from 6 to 3 | 7 | 7 | 8 | 7.3 |
| 3 | Add progress bar + estimated time to onboarding | 6 | 6 | 9 | 7.0 |
| 4 | Trigger email nudge 24h after onboarding stall | 7 | 6 | 7 | 6.7 |
| 5 | Segment by traffic source and personalize onboarding | 8 | 5 | 4 | 5.7 |
5. Tracking Gaps
- **Missing:** Time spent on each onboarding step
- **Missing:** Rage click / error events during project creation
- **Missing:** Segment data by traffic source at each stage
- **Missing:** "Return visit" tracking (did users come back after dropping off?)
- **Recommended tool:** Add session replay (e.g., PostHog, FullStory) on onboarding + project creation flows
Tips for Best Results
- 💡Include raw numbers, not just percentages — the AI can calculate conversion rates and spot statistical significance issues.
- 💡Mention any recent product or pricing changes so the AI can factor them into its hypotheses.
- 💡Segment your funnel by traffic source before feeding it in — paid traffic and organic traffic often have very different funnel shapes.
- 💡Re-run this monthly to track whether your experiments are actually moving the needle.
Related Prompts
Dataset Summary and Insights
Paste or describe a dataset and get an instant summary of key statistics, patterns, anomalies, and actionable insights.
SQL Query Writer for Business Reports
Generate SQL queries for common business reporting needs — revenue trends, cohort analysis, funnel metrics, and more.
Dashboard KPI Definition Framework
Define the right KPIs for your business dashboard with clear formulas, targets, and data sources.