What's new in The AI Creative Brief System

Summary

Agent Codebase 20 → 24 commands. Module 24 added (Autogrowth + Closed Creative Feedback Loop). Net-new: demandgen-autogrow, creative-refresh-review, seasonal-creative-refresh, spy-demand-sidecars. AI image/video framework refreshed with Bayesian asset posteriors and multi-aspect video standards.

Highlights

• Agent Codebase — 20 → 24 commands (+4 net-new)
• demandgen-autogrow — Weekly DG diagnose → mutate → promote → retire loop, dry-run default
• creative-refresh-review — 13-Point Creative v10.5 pre-ship scoring — <70 reworks, 70-85 ships with watch tag, 85+ promotion candidate
• seasonal-creative-refresh — Rotates creative library on seasonal cadence based on account-specific seasonality
• spy-demand-sidecars — DG-specific competitor signals: pause/launch velocity, theme saturation, channel mix
• Closed creative feedback loop — Every generated asset scored, every promoted asset tracked, every retired asset informs next generation
• Module 24 added — Autogrowth + Closed Creative Feedback Loop

Full release notes

Scope: Agent Codebase 20 → 24 commands. Blueprint 23 → 24 modules (Module 24: Autogrowth + Closed Creative Feedback Loop).

Net-new commands (+4): demandgen-autogrow (weekly DG diagnose → mutate → promote → retire loop), creative-refresh-review (13-Point Creative v10.5 pre-ship scoring), seasonal-creative-refresh (rotates creative library on seasonal cadence based on account-specific seasonality), spy-demand-sidecars (DG-specific competitor signals — pause/launch velocity, theme saturation, asset rotation patterns, channel mix).

AI image/video framework refresh: Standardized campaign brief schema. Direct-response creative standards (measurable claim, single action, specificity minimums). Closed creative feedback loops — every generated asset scored, every promoted asset tracked, every retired asset informs the next generation. Bayesian asset posteriors. Multi-aspect video standards (9:16 / 16:9 / 1:1) with format-specific pacing rules.

Curriculum updates: Module 24 added. Tier-comparison table updated with autogrowth loop + creative feedback rows.

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