What's new in The Attribution & Measurement System

Summary

Agent Codebase 21 → 24 commands. Module 6 added (Page Review Panel Signals in Attribution). Net-new: presell-review, offer-review, presell-review-backfill — the same Page Review Panel that gates deploys now feeds attribution. brand-calibrate extended with expert reviewer weighting.

Highlights

• Agent Codebase — 21 → 24 commands (+3 net-new)
• Page Review Panel signals — presell-review + offer-review + presell-review-backfill feed page-health signals into attribution
• brand-calibrate — Re-weights expert reviewers per brand based on which reviewer's scores best predict real conversion outcomes
• Page-health → optimization — Low-health pages deprioritized in budget allocation, high-health pages scaled
• Page-health → reporting — Page-health surfaces in brand-pdf-report and brand-digest
• Module 6 added — Page Review Panel Signals in Attribution
• Positioning shift — Attribution is no longer just analytics + experiment infra — it's a page-quality intelligence layer

Full release notes

Scope: Agent Codebase 21 → 24 commands. Blueprint 5 → 6 modules (Module 6: Page Review Panel Signals in Attribution).

Net-new commands (+3): presell-review, offer-review, presell-review-backfill — the same Page Review Panel that gates page deploys (in the Landing Page System) is consumed here as an attribution signal source.

Attribution layer changes: Page-health signals consumed by attribution. Every deployed page gets a review history, an expert reviewer score with per-reviewer weighting, and a combined page-health score. brand-calibrate re-weights expert reviewers per brand based on which reviewer's scores best predict real conversion outcomes. Page-health score becomes an input to campaign-level optimization — low-health pages get deprioritized in budget allocation, high-health pages get scaled. Page-health surfaces in brand-pdf-report and brand-digest. Phase 0 objective brief required on every review + reporting artifact.

Positioning shift: Attribution & Measurement is no longer just analytics infrastructure and experiment infrastructure. It's now also a page-quality intelligence layer. Tracking → attribution → experiments → page-health signals → optimization. One layered measurement stack instead of three disconnected ones.

Curriculum updates: Module 6 added. Tier-comparison table updated with Page Review Panel signals row. Three-choice CTA strip refreshed.

Global framework changes (apply across every product)

• Phase 0 objective brief required on presell, offer, Search, PMax, Demand Gen, and review artifacts before generation begins
• Page Review Panel where relevant — scanner + expert reviewer scoring, P0/P1/P2 findings, combined page-health score, trust-level gating
• PMax safety defaults — URL expansion always OFF, dry-run mutations, explicit --apply required
• Search framework rules — exact-match only, CPC floor/ceiling, IF-function ban, single DKI per RSA, headline composition standards
• Canvas-design default — saved themes opt-in only via theme=<name> or explicit --auto-match flag
• AI image/video framework refresh — campaign brief fields, DR creative standards, creative feedback loops, asset posteriors, multi-aspect video standards
• AutoResearch eval system — review eval buckets added for presell-review and offer-review
• Claude Code + Codex compatibility — CLAUDE.md remains the Claude Code entrypoint; AGENTS.md symlinked for Codex

Security / client-readiness

• No API keys, OAuth secrets, service-account files, .env files, or runtime state files shipped in any codebase
• No source-brand or client names included
• No maintainer-local paths included
• MCP configs use placeholders or environment variables only
• READMEs reflect current command counts and current 2026-04 product positioning