AnalyticsFunnels, cohorts and retentionIntermediateAnalyses your data

Conversion funnel drop-off analysis with hypotheses and tests

Finds the biggest relative and absolute drop-offs in a funnel table and turns them into prioritised, testable hypotheses.

For: Performance marketers, Marketing analysts, Growth marketers · Works with: Any capable chat model (ChatGPT, Claude, Gemini, others), Google Analytics 4, Google Sheets / Excel

Public beta. This prompt was drafted with AI assistance and checked by automated rules, but it has not been reviewed or tested by a person yet. Treat it as a starting point and check the output. It is hidden from search engines while in beta. Use the “Was this prompt useful?” box to tell us what works.

Your prompt

Act as a conversion-rate analyst. Analyse the funnel below for September 2026. Funnel type: ecommerce checkout. Counting unit: sessions. Data (step | count): Step | Count Product page view | 52000 Add to cart | 7800 Begin checkout | 3900 Add shipping info | 3000 Purchase | 1900 Segments available (if any): device, new vs returning, traffic source. Tasks: 1. State assumptions (for example whether steps are strictly sequential, whether users can skip steps, and how counts were derived). 2. Compute step-to-step conversion and overall conversion with formulas, and verify that no step has more than its predecessor unless the funnel allows skipping; flag inconsistencies. 3. Identify the largest drops in relative and absolute terms, and say which matters more for increase purchases without raising ad spend. 4. For each major drop, list hypotheses in three groups: measurement or tracking issues, user-intent or traffic-mix issues, and experience or friction issues. Label all as hypotheses and name the data that would test each. 5. Propose a prioritised test list with one change per test and the metric to judge it by. 6. State what you cannot conclude (for example why users dropped). Rules: do not invent benchmarks, drop-off reasons or numbers. If data is missing or not provided, say so. Verify calculations by recomputing. Distinguish observation from hypothesis.

Customize

The fields start with example values so you can see how the prompt works. Everything stays in your browser.

Period.

What the funnel is.

Users or sessions.

Paste your table. The default is small fictional sample data so the preview works; replace it with your own.

What cuts you can pull.

What matters.

Example of what to expect

Illustrative only. It describes the kind of result this prompt aims for; real output varies by tool, model and run.

Step conversion rates with formulas, an integrity check, the largest relative and absolute drops, grouped hypotheses with tests, a prioritised one-change-per-test list and limits. (Illustrative.)

Expected format: Assumptions, conversion table, biggest drops, hypotheses, test list.

How to use it

  1. Verify the funnel counts come from consistent definitions.
  2. Segment the biggest drop before testing.
  3. Run one test at a time.

Limitations

  • Funnel data shows where users leave, not why.
  • Mixing sessions and users breaks the math.

Platform notes

Any capable chat model (ChatGPT, Claude, Gemini, others)

Official docs read · checked 2026-10-11

Works in any capable chat model. Paste a small anonymised sample and recompute the key numbers yourself: chat models can misread columns or miscalculate, and they cannot run your statistical tests reliably.

General notes on Any capable chat model (ChatGPT, Claude, Gemini, others)
  • These prompts are plain text and work in any chat assistant. For analytics prompts, paste a small, anonymised export; a chat model can misread columns or miscalculate, so recompute key numbers yourself.

Google Analytics 4

Official docs read · checked 2026-10-11

GA4 exports and the interface can differ (sampling, thresholds, attribution, data freshness); state which one your numbers came from.

General notes on Google Analytics 4
  • The BigQuery export has daily events_YYYYMMDD tables and intraday tables; intraday lacks some fields, and late-arriving data can update a daily table for up to 3 days.
  • Exported data and the GA4 interface can differ; the export documentation links to separate comparison articles that we did not read.

Google Sheets / Excel

Not verified: third-party guidance only · checked 2026-10-11

Test any formulas on a small range first; syntax depends on locale and version.

General notes on Google Sheets / Excel
  • Formulas are written for common functions in both products. Locale settings (decimal and argument separators) can change what you must type.

Source, license and attribution

Origin
Original by MarketerTools
Publisher
MarketerTools
License
Original work by MarketerTools, free to copy and use. Informed by the linked documentation; no third-party text is reproduced.
Platform assumptions checked
2026-10-11

Documentation and references behind this prompt

These informed the structure and the platform notes. A reference is not a license, and no third-party prompt text is copied here.

Spotted an attribution error, or are you a source owner with a request? Use the chat button at the bottom right and quote prompt ID ana-031. We will correct or remove it.

Related prompts

  • AnalyticsIntermediateAnalyses your data

    Landing-page conversion diagnostics from GA4 data

    Identifies which landing pages underperform for their traffic and proposes testable hypotheses, including tracking and intent mismatches.

    Google Analytics 4 · Any capable chat model (ChatGPT, Claude, Gemini, others)

  • AnalyticsAdvancedWrites SQL / queries

    Write BigQuery SQL: ordered funnel from GA4 events

    A prompt for a user- or session-level funnel query that respects event order and time windows, with explicit decisions about what counts as a step.

    BigQuery / SQL · Google Analytics 4 · Any capable chat model (ChatGPT, Claude, Gemini, others)

  • AnalyticsIntermediateAnalyses your data

    A/B test result evaluation with statistical guardrails

    Interprets an A/B test from raw counts with checks for sample-ratio mismatch, peeking and practical significance, without inventing a significance result.

    Any capable chat model (ChatGPT, Claude, Gemini, others) · Google Sheets / Excel

  • AnalyticsIntermediateAnalyses your data

    Cohort retention analysis and interpretation

    Turns a cohort table into retention curves and a careful read of what changed between cohorts, with hypotheses clearly separated from findings.

    Any capable chat model (ChatGPT, Claude, Gemini, others) · Google Analytics 4 · Google Sheets / Excel