Team,

v2: updated with this afternoon's changes. The plan, dates and cadence below are unchanged from v1.

We're kicking off AI*Right, the first major project run by our Grok bot team. Every gate is approved by a named human.

WHAT IT IS
AI*Right is Scale's enterprise-by-default control layer for AI agents: Agent = Harness + Model (through an AI Gateway) + Governed MCP (MCP Gateway + Registry). Every model call goes through the AI Gateway and every tool call through the MCP Gateway. Nothing connects directly. We deliver it as Assess, Architect, Deliver, Manage, and it complements Cloud iQ.

PROJECT PLAN

PhaseDatesOutcome
1. AssessOct 20 – Nov 2, 2026Maturity baseline, gaps, risks; pilot confirmed
2. PilotNov 3 – Nov 30, 2026One governed workflow: reference harness, audit log schema, minimal dual gateways, human approval gate
3. Core Control PlaneDec 1 – Dec 18, 2026AI Gateway, MCP Gateway and Registry in production posture; identity and policy-as-code
4. Connectors & ScaleJan 2027 onwardMore MCP servers, multi-agent patterns
5. Ops & AlignmentIn parallel from Dec 2026Observability, FinOps, KPIs
6. ManageQ1 2027 onwardOngoing managed service and compliance validation

AI*Right Project Plan Flow

THE WIREFRAME: HOW A GOVERNED REQUEST FLOWS

  1. Request: a user or agent asks for work.
  2. Authorize: identity and on-behalf-of scope are checked first.
  3. Choose Brain: the AI Gateway routes to the right model.
  4. Govern & Route: the MCP Gateway applies policy, limits and PII rules. Any write waits here for human approval.
  5. Resolve: the Registry returns only approved, healthy, version-pinned servers.
  6. Execute: the MCP server performs one scoped action.
  7. Observe: audit, FinOps and feedback, with every step logged.

Five pillars: Agents; Security & Identity; Core Control Plane; Data & Memory; Operations & Alignment.

AI*Right Request Lifecycle Wireframe

WHERE WE ARE (Oct 19, 2026)

WHAT CHANGED TODAY (Oct 19, afternoon)

YOUR INPUT NEEDED: FLAG BY FRI OCT 23

#ItemOwnerProposed answer
1Console phase placement (G31): approve Ed's P1–P6 proposal?Pam reviews; Jon approvesEd's P1–P6 plan; watch Phase 3 load (14 working days)
2Pilot document countPam; Jon picksUNKNOWN. Needed before Pilot entry Nov 3
3Is Fri Nov 27 a Scale holiday?JonUNKNOWN. Pilot is 19 working days, 18 if off
4Approval screen for the PilotEd + PamThin approver inbox; alternative is LiteLLM's built-in UI (untested)
5Who builds the console front end?JonUNKNOWN. No owner in the RACI
6How client users map to a tenant (Entra tenant, guest, or Okta)Ed; Jon (identity)UNKNOWN. Decide in Assess
7Go-live tenant (lab vs Azure/AWS) and Entra ID confirmationJon; EdEntra ID assumed; tenant UNKNOWN. Due Nov 2
8Production gateway identity: mTLS and/or gateway-signed tokenEdUNKNOWN. Options listed; none tested
9Cloudflare token for Clef (Workers AI) + spendJonNot requested. Clef stays off until approved
10Witnessed re-runs for G30, G32, G39PamDate UNKNOWN

Full list: open-items-for-team.md in the AI*Right workspace.

HOW WE'LL COMMUNICATE

WHAT I NEED FROM YOU
Flag any concern with the dates, and your answers to the table above, by Fri Oct 23.

Jon