What you do
- Name the affected accounts and campaigns, what changed, the KPI, and the comparison window.
- Provide exports or select one read-only provider route.
- Review the diagnosis before starting any mutation workflow.
Paid-media teams diagnosing performance changes before acting / media buying
A source-linked diagnosis with ranked hypotheses, evidence gaps, and a recommendation for no change, budget review, creative work, or an experiment.
The problem
AI can compare multiple causal categories and time windows systematically while keeping uncertainty and business judgment visible.
What you do
What the agent does
When this workflow helps
Before it starts
What proves it worked
Workflow path
A real run expands these stages around the request, context, selected tools, approvals, and dependencies.
Read the review scope, metric targets, recent snapshots, related learnings, and active experiments.
Execute only the selected read action that the concrete run plan grants for missing evidence.
Compare evidence against targets and separate likely channel, audience, creative, landing page, and budget drivers.
Store recommended follow-up resources, budget review notes, and learning candidates for later review without executing a mutation.
Safe stopping and recovery
Documented follow-on work
Allocation is a supported cause and budget movement should be reviewed.
conditionalMedia Buying Creative Variant GenerationCreative fatigue or mismatch is a supported cause.
conditionalLanding Page And Creative ExperimentThe evidence supports a measured creative or destination experiment.
Specialists inside this workflow
Connected work