AnalyticsGA4 analysisIntermediateWrites a report

GA4 weekly channel performance summary from an export

Summarises a GA4 channel export into a short report of what changed, with every figure computed from your data and every explanation labelled as a hypothesis.

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

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

You are a careful marketing analyst. Analyse the GA4 export below for 7-13 Oct 2026 (compared with 30 Sep-6 Oct 2026). Business goal: increase free-trial signups. Conversion/key event definition: key event 'trial_start' counts once per user per day. Currency: USD. Data (columns as exported): Channel | Sessions | Engagement rate | Key events Organic Search | 4200 | 61% | 126 Paid Search | 2100 | 48% | 98 Direct | 1800 | 55% | 40 Email | 700 | 66% | 49 Do this in order: 1. List the columns you were given and any definitions you are assuming (for example how engagement rate is calculated). State every assumption. 2. Produce a table by channel with the metrics present in the data, plus the change versus the comparison period computed from the data only. 3. Write 3-5 observations, each citing the exact numbers behind it. 4. Offer up to 3 hypotheses for the biggest changes. Mark them as hypotheses, say they show correlation not causation, and say what extra data would test each. 5. List missing data that limits the analysis (for example traffic-source attribution model, tagging gaps, consent-related loss). Rules: do not invent numbers, benchmarks or channels that are not in the data. If something needed is missing or not provided, say so instead of estimating. Before answering, recalculate every percentage change and verify totals match the table.

Customize

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

Period covered by the export.

Previous period, or write 'none provided'.

What matters most.

Exactly how conversion is counted.

For any revenue columns.

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

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.

A column and assumptions list, a channel table with period-over-period changes computed from the data, 3-5 numbered observations, hypotheses flagged as correlation, and a list of missing data. (Illustrative.)

Expected format: Assumptions, channel table, observations, hypotheses, missing-data list.

How to use it

  1. Export a GA4 report and paste a small table.
  2. Check the model's table against your export before sharing.
  3. Test hypotheses with extra data before acting on them.

Limitations

  • The model sees only what you paste; it cannot detect tracking errors by itself.
  • GA4 interface numbers and exports can differ; do not mix sources in one comparison.

Platform notes

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.

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 export and recompute the key numbers yourself: chat models can misread columns or miscalculate.

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.

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-001. We will correct or remove it.

Related prompts

  • AnalyticsIntermediateAnalyses your data

    GA4 traffic-quality check: engagement vs conversion by source

    Separates sources that bring visits from sources that bring valuable visits, ranking by engagement and conversion with sample-size warnings.

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

  • 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)

  • AnalyticsIntermediateWrites a report

    Executive marketing report narrative with variance analysis

    Writes a concise executive narrative from your KPI table: what moved, by how much, plausible reasons labelled as hypotheses, and decisions needed.

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

  • AnalyticsIntermediateBuilds a checklist

    GA4 sudden traffic or conversion drop triage

    A structured triage that separates tracking and measurement problems from real demand changes, in the order a careful analyst would check them.

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