Marketing Swarm

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-mutation

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-analysis

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.

host-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.

sandbox-python-executor

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.