Prompts for GA4, Google Ads, Meta Ads, Search Console, SQL, unit economics, attribution and experiments. Each one forces the model to state assumptions, check its own arithmetic and avoid inventing data.
40 prompts
40 prompts
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.
Google Analytics 4 · Any capable chat model (ChatGPT, Claude, Gemini, others)
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)
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)
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)
Reviews your event list and key-event setup for naming, duplication, missing parameters and gaps against a measurement plan.
Google Analytics 4 · Any capable chat model (ChatGPT, Claude, Gemini, others)
Gets a correct, cost-aware GA4 export query by giving the model your table path, session definition, window and required columns.
BigQuery / SQL · Google Analytics 4 · Any capable chat model (ChatGPT, Claude, Gemini, others)
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)
Explains why GA4 and an ad platform report different conversions, by listing likely definitional causes and the checks to confirm each one.
Google Analytics 4 · Google Ads · Meta Ads +1
Groups search terms by pattern, estimates wasted spend from your data and proposes negatives, with a protected 'do not negate' list and match-type cautions.
Google Ads · Any capable chat model (ChatGPT, Claude, Gemini, others)
Compares campaigns against your target, separates volume, efficiency and conversion-rate drivers, and highlights what the data cannot explain.
Google Ads · Any capable chat model (ChatGPT, Claude, Gemini, others)
Reviews headline and description asset reports for patterns and proposes new assets, while flagging how little asset-level data can prove.
Google Ads · Any capable chat model (ChatGPT, Claude, Gemini, others)
Checks whether a budget is on pace for the month and whether lost impression share is budget-limited or rank-limited, using the figures you provide.
Google Ads · Any capable chat model (ChatGPT, Claude, Gemini, others)
Reviews keyword lists and match types for overlap, intent mixing and cannibalisation, with the data you need to confirm each finding.
Google Ads · Any capable chat model (ChatGPT, Claude, Gemini, others)
Gets a GAQL query for a specific report, with explicit instructions to confirm field names, unit conventions and segment compatibility.
Google Ads · Any capable chat model (ChatGPT, Claude, Gemini, others)
Turns a Meta Ads export into a weekly narrative with computed metrics, flagged anomalies and carefully worded explanations.
Meta Ads · Any capable chat model (ChatGPT, Claude, Gemini, others)
Looks for fatigue signals (rising frequency, falling CTR, rising cost per result) in ad-level trend data and separates them from other explanations.
Meta Ads · Any capable chat model (ChatGPT, Claude, Gemini, others)
Interprets breakdown reports without falling for mix-shift traps: checks volumes, compares like with like and flags where aggregates can mislead.
Meta Ads · Any capable chat model (ChatGPT, Claude, Gemini, others)
Interprets results exported with several attribution windows so you understand how much of reported performance depends on window and view-through credit.
Meta Ads · Any capable chat model (ChatGPT, Claude, Gemini, others)
Finds queries where an improvement is plausible (decent impressions, mid-ranking, low CTR) and suggests page-level actions as hypotheses.
Google Search Console · Any capable chat model (ChatGPT, Claude, Gemini, others)
Breaks a traffic decline into impressions, CTR and position changes by page and query so the right class of cause is investigated first.
Google Search Console · Any capable chat model (ChatGPT, Claude, Gemini, others)
Finds queries where several of your pages compete, and helps decide whether it is harmful or harmless before merging or redirecting anything.
Google Search Console · Any capable chat model (ChatGPT, Claude, Gemini, others)
Produces a transparent CAC-by-channel query once you describe spend and customer tables, with attribution rules stated explicitly rather than assumed.
BigQuery / SQL · Any capable chat model (ChatGPT, Claude, Gemini, others)
A code-review prompt for existing SQL: correctness first, then cost and readability, with changes explained and a test for equivalence.
BigQuery / SQL · Any capable chat model (ChatGPT, Claude, Gemini, others)
Gets working formulas for KPIs from your actual column layout, with error handling, a test case and explanations you can audit.
Google Sheets / Excel · Any capable chat model (ChatGPT, Claude, Gemini, others)