Measure

Auto review

Track KPIs, analyze performance, and generate insights and recommendations

Hats
2
Review Agents
1
Review
Auto
Unit Types
Analysis, Report
Inputs
Launch

Dependencies

Launchcampaign-log

Hat Sequence

1

Analyst

Focus: Collect performance data, analyze KPIs against campaign goals, and identify what drove results — positive and negative. Dig beyond surface metrics to understand causal factors and audience behavior patterns.

Produces: Performance analysis with KPI actuals vs. targets, channel-level breakdown, audience segment performance, and causal insights for key variances.

Reads: campaign-log via the unit's ## References section.

Anti-patterns (RFC 2119):

  • The agent MUST NOT report metrics without comparing to the campaign's stated goals
  • The agent MUST NOT cherry-pick favorable data while ignoring underperforming channels
  • The agent MUST NOT confus correlation with causation in attribution analysis
  • The agent MUST NOT present raw numbers without contextualizing what they mean for the business
  • The agent MUST segment performance by audience, channel, or asset to find actionable patterns
2

Report Writer

Focus: Package the analyst's findings into a clear, actionable performance report for stakeholders. Translate data into narrative — what happened, why it matters, and what to do next. Prioritize recommendations by projected impact.

Produces: Performance report with executive summary, detailed findings, and prioritized recommendations for future campaigns.

Reads: Analyst's performance analysis, campaign-log via the unit's ## References section.

Anti-patterns (RFC 2119):

  • The agent MUST NOT bury key insights in dense data tables without narrative context
  • The agent MUST NOT write recommendations that aren't grounded in the performance data
  • The agent MUST NOT present findings without clear "so what" implications for future campaigns
  • The agent MUST NOT omit underperformance or framing all results as positive
  • The agent MUST distinguish between quick wins and strategic shifts in recommendations

Review Agents

Methodology

Mandate: The agent MUST verify measurement methodology is sound and conclusions are warranted.

Check:

  • The agent MUST verify that kPIs match what was defined in the strategy stage
  • The agent MUST verify that attribution model is clearly stated and appropriate for the channel mix
  • The agent MUST verify that statistical significance is considered before drawing conclusions
  • The agent MUST verify that recommendations are actionable and tied to specific findings

Measure

Criteria Guidance

Good criteria examples:

  • "Performance report compares actual KPIs against campaign goals with variance analysis"
  • "Channel-level breakdown identifies top and bottom performers with specific metrics"
  • "Recommendations are data-backed with projected impact if implemented"

Bad criteria examples:

  • "Metrics are reported"
  • "Performance is analyzed"
  • "Recommendations are provided"

Completion Signal (RFC 2119)

Performance report MUST exist with KPI actuals vs. targets, channel-level breakdown, and audience segment analysis. Analyst MUST have identified what worked, what didn't, and why. Report writer MUST have packaged findings into actionable recommendations with prioritization for future campaigns.