Phase 1 extended composer, manual rail, Brand Kit, settings, and MCP with ten creative-depth features. Phase 2 assumes those surfaces exist and adds downstream operational AI: agent runs with gates, metric-aware refinement, personalization assembly, derivative assets, locale law packs, interactive MIME, governance suite, and federated tool scopes.
| C-ID | Primitive | Primary feature |
|---|---|---|
| C-98 | Orchestration timeline / plan graph row | 01 Agentic Orchestrator |
| C-99 | Live KPI strip (contextual metrics) | 02 Performance Loop |
| C-100 | AMP module shell + validation status | 06 AMP for Email |
| C-101 | Shield evaluation summary panel | 07 Mailchimp Shield |
| C-102 | Cross-domain MCP tool registry row | 08 Cross-domain agent |
Features 03–05 primarily compose Phase 1 primitives (C-46, C-82, C-89, C-23, C-61) with new /v.phase2-* variants (register alongside Phase 1’s variant catalog).
| Feature | Plan / brief | Composer | Editor canvas | Settings / admin | Reporting |
|---|---|---|---|---|---|
| 01 Orchestrator | ● | ○ | ○ | ○ | ○ |
| 02 Performance loop | ○ | ○ | ● | ○ | ● |
| 03 Send-time personalization | ○ | ● | ● | ○ | ○ |
| 04 Asset studio | ○ | ○ | ● | ● | ○ |
| 05 Localization | ● | ○ | ● | ● | ○ |
| 06 AMP email | ○ | ○ | ● | ○ | ○ |
| 07 Shield | ○ | ○ | ○ | ● | ● |
| 08 Cross-domain agent | ○ | ● | ○ | ● | ○ |
● primary surface · ○ secondary touches. Heatmap is directional for staffing, not a maturity score.
Freddie proposes multi-step graphs (brief → creative → audience → schedule). Each edge requires explicit approval; exports an audit row for Shield. Uses C-98 plus existing composer strategy fields.
Campaign objects already live in Mailchimp — orchestration attaches to real sends, not slides.
While editing or reviewing an active send, a C-99 strip shows cohort KPIs. On regression, Freddie proposes a scoped edit with preview diff (reuses C-43/v.preview-diff).
Dimensionality (affinity, tier, locale) maps to content cells. Blocked cells surface rule ids (R8-policy). Simulator uses profile fixtures from audience service.
Exports align to channel safe zones; ties into Universal Content / Content Studio roadmap. Changing the master marks derivatives stale with batch refresh.
Packs combine legal text, price/promo rules, and Brand Voice per region. Hard stops prevent schedule when mandatory blocks missing.
C-100 wraps validated AMP snippets; publishing emits multipart structure with paired static HTML per best practice.
C-101 aggregates scanners + human roles. Designed for enterprise procurement stories (not bolt-on “AI trust badges”).
Extends Phase 1 MCP with C-102 tool registry rows and per-domain credentials. Same campaign graph surfaces in support context.
| Variant ID | Base | Feature | Note |
|---|---|---|---|
| C-43/v.performance-suggestion | Assistant body | 02 | Embeds KPI delta + proposed action |
| C-46/v.personalization-matrix | Goal / strategy fields | 03 | Highlights suppressed cells |
| C-23/v.locale-blocker | Banner | 05 | Hard-stop with pack id + fix CTA |
| C-90/v.scoped-mcp-tools | Token / integrations row | 08 | Lists enabled external tools |
| C-91/v.shield-section | Settings popover | 07 | Labeled Shield policies + approvers |
| # | Step | Features | Rationale |
|---|---|---|---|
| 1 | Shield policy engine + audit store | 07, 01 | Orchestrator checkpoints require durable policy evaluation |
| 2 | Localization packs + mandatory blocks | 05 | Unblocks international sends before personalization expands |
| 3 | Live metrics ingress + C-99 strip | 02 | Feeds the refinement loop early |
| 4 | Assembly-time personalization engine | 03 | Uses packs + Shield outcomes |
| 5 | Asset derivative graph | 04 | Depends on stable asset IDs from Phase 1 content surfaces |
| 6 | AMP validator + MIME publisher | 06 | Isolated pipeline; pair with rendering tests |
| 7 | Cross-domain MCP registry | 08 | External OAuth + scoped tokens last |
Cross-refs: Phase 1 execution · Design Audit · Canva-gap analysis