Analyze paid media end to end
A set of specialist marketing workflows for diagnosing campaign performance, evaluating spend risk and pacing, comparing budget allocations, breaking down creative patterns, planning creative refreshes, simulating scenarios, auditing attribution and incrementality, learning from campaign history, and checking recommendation quality. It works from data supplied by the user or data available through authorized host tools. More
Skills 11 in the ChatGPT listing
Budget & Media Allocation Use when deciding how to distribute paid-media budget across campaigns, audiences, geographies, or platforms, including cross-platform comparisons and attention-cost opportunities. Campaign Diagnostics Use when paid-media performance changed, spend looks abnormal, delivery or pacing is off, or the user wants an account/campaign health diagnosis before choosing tactics. Causal Attribution Use for attribution disputes, incrementality questions, causal claims, holdout or lift-test review, counterfactual analysis, and cases where platform-reported credit may not represent true business impact. Creative Fatigue Use when an ad may be fatiguing, the user needs refresh timing, or they want new variants derived from proven creative elements while preserving a clear testing logic. Creative Genome Use to analyze one or more ads or creative variants, identify the message and execution patterns associated with performance, and turn winners into testable creative hypotheses without copying them blindly. Decision Quality Gate Use before finalizing high-impact marketing recommendations or whenever multiple analyses disagree, evidence is weak, causal language may be overstated, or a live campaign change is being considered. Workspace Operator Use when a Marketing Swarm workflow needs to inspect, search, modify, or verify files in the host workspace using the safest native tools available. Marketing Memory Use when the user has prior campaign results, experiments, creative history, or benchmarks and wants to find comparable past evidence, reusable patterns, or lessons relevant to a current decision. Marketing Swarm Router Use for broad or multi-part paid-media questions that need routing across campaign diagnosis, budget allocation, creative analysis, fatigue planning, simulation, attribution, historical evidence, and quality review. Marketing Python Use when Marketing Swarm needs deterministic metric calculation, tabular analysis, simulation, statistical checks, file processing, or verification that should actually run with host-native Python instead of relying on unverified mental arithmetic. Scenario Simulation Use for campaign what-if questions, budget or KPI forecasts, sensitivity analysis, and decision ranges where deterministic or probabilistic scenarios are more useful than a single point estimate. 