Analyze Your Product Funnel and Find the Biggest Drop-Off to Fix First

Paste your funnel step counts and get a conversion table, the largest leak flagged with reasoning, and one testable fix per step with an expected lift range.

You getFunnel table, biggest leak and fix table

Prompt

Prompt
Act as a senior product analyst who runs conversion experiments.

Your job is to analyze the product funnel I will paste right after this prompt. It will list each step and the number of users who reached it. If the time window, the product type, or the order of steps is unclear, first ask me up to 3 short numbered questions in one message and wait for my answers.

Rules:
1. Show every calculation to one decimal place: step conversion, users lost, and cumulative conversion from the first step.
2. Flag the largest leak by both percent lost and users lost. If they differ, pick one to fix first and explain why in 2 sentences.
3. Give exactly one testable fix per step transition. Each fix needs a hypothesis, a concrete test, and one success metric.
4. Give each fix an expected relative lift range, clearly labeled as your assumption. Do not cite industry benchmarks or statistics.
5. For the top fix, calculate how many extra end-of-funnel users the low and high end of the range would produce.

Output format:
- Funnel table: Step | Users | Step conversion | Users lost | Cumulative conversion
- Biggest leak (3-4 sentences)
- Fix table: Transition | Likely cause | Test | Success metric | Expected lift
- Impact of top fix
- Data gaps: what is missing that could change these conclusions.

Example output

At a glanceUsers remaining at each funnel stepB2B analytics SaaS free-trial funnel, last 30 days; biggest leak is step 4 to 5
  • Landing page visit: 48,000
  • Clicked Start free trial: 9,600
  • Completed signup form: 5,760
  • Verified email: 4,032
  • Connected a data source: 1,613
  • Built first dashboard: 1,210

Example for: a B2B analytics SaaS free-trial funnel, last 30 days, all traffic sources.

Funnel Table

StepUsersStep conversionUsers lostCumulative conversion
1. Landing page visit48,000——100.0%
2. Clicked Start free trial9,60020.0%38,40020.0%
3. Completed signup form5,76060.0%3,84012.0%
4. Verified email4,03270.0%1,7288.4%
5. Connected a data source1,61340.0%2,4193.4%
6. Built first dashboard1,21075.0%4032.5%

Biggest Leak

By users lost, the landing page is largest (38,400), but much of that is low-intent traffic you can't fully fix inside the product. By percent lost among committed users, Verified email → Connected a data source is worst: 60.0% of people who already signed up and verified never connect data. Fix this first because these users have shown clear intent, and every gain flows straight to activation at a 75.0% rate.

Fix Table

TransitionLikely causeTestSuccess metricExpected lift
1 → 2Value unclear above the foldHeadline naming the outcome plus a 20-second product clipTrial click rate+5% to +15%
2 → 3Form asks for company size and phoneCut the form to email and password onlyForm completion+10% to +20%
3 → 4Verification email lands late or in spamLet users continue before verifying; send a reminder after 1 hourVerification rate+5% to +12%
4 → 5Connecting data needs admin credentials users lackOffer a sample dataset plus an Invite your admin buttonData connection rate+15% to +35%
5 → 6Blank canvas after connectingAuto-generate a starter dashboard from the connected sourceFirst dashboard rate+5% to +10%

Impact of Top Fix

  • Low end (+15%): step 5 conversion rises from 40.0% to 46.0% → 1,855 connect → about 1,391 activated (+181 per month).
  • High end (+35%): step 5 conversion rises to 54.0% → 2,177 connect → about 1,633 activated (+423 per month).

Data Gaps

  • No split by traffic source; paid traffic may be dragging down step 1 → 2.
  • No time-to-step data, so some step 5 users may still be connecting after the window closed.
  • Lift ranges are assumptions; size your test to detect at least a 15% relative change.
Written by AI from this prompt. Your results will vary.

Tips and common edits

Why this works

  • Requiring both percent lost and users lost stops the model from always blaming the top of funnel, where traffic quality distorts results.
  • One fix per transition with a hypothesis and success metric turns analysis into a ready experiment backlog.
  • Labeling lift ranges as assumptions and converting them to extra users keeps estimates honest and easy to prioritize.

Use this after a launch or monthly review when you have step counts from your analytics tool. Paste the counts into ChatGPT, Claude or Gemini with the date range and step names.

Common edits

  • Add a segment split, such as mobile vs. desktop, and ask for a separate table per segment.
  • Ask for a minimum sample size per variant for the top fix so you can plan test duration.

Prompt details

By
Prompts-GPT editors
Published

Did this prompt work?

Keep exploring

More in Product Management