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
| Phase | Dates | Outcome |
|---|
| 1. Assess | Oct 20 – Nov 2, 2026 | Maturity baseline, gaps, risks; pilot confirmed |
| 2. Pilot | Nov 3 – Nov 30, 2026 | One governed workflow: reference harness, audit log schema, minimal dual gateways, human approval gate |
| 3. Core Control Plane | Dec 1 – Dec 18, 2026 | AI Gateway, MCP Gateway and Registry in production posture; identity and policy-as-code |
| 4. Connectors & Scale | Jan 2027 onward | More MCP servers, multi-agent patterns |
| 5. Ops & Alignment | In parallel from Dec 2026 | Observability, FinOps, KPIs |
| 6. Manage | Q1 2027 onward | Ongoing managed service and compliance validation |
THE WIREFRAME: HOW A GOVERNED REQUEST FLOWS
- Request: a user or agent asks for work.
- Authorize: identity and on-behalf-of scope are checked first.
- Choose Brain: the AI Gateway routes to the right model.
- Govern & Route: the MCP Gateway applies policy, limits and PII rules. Any write waits here for human approval.
- Resolve: the Registry returns only approved, healthy, version-pinned servers.
- Execute: the MCP server performs one scoped action.
- Observe: audit, FinOps and feedback, with every step logged.
Five pillars: Agents; Security & Identity; Core Control Plane; Data & Memory; Operations & Alignment.
WHERE WE ARE (Oct 19, 2026)
- All 9 roles assigned. Ed Engineering: Framework Architect, Agent & Harness Designer, MCP & Integration, Security & Identity (interim). Pam the PM: Governance & Compliance Lead, Delivery Program Manager. Oz: KB Curator, Gap & Risk Analyst, Observability & FinOps (interim).
- Pressure test held today; decisions logged.
- Pilot 1: internal-only governed document review on Scale's own non-sensitive documents. Synthetic test documents first, no client data, and a human approves before any write.
- Pilot gateway: self-hosted LiteLLM, with Kong targeted for Phase 3.
- Independence: bots witness and log the tests; I sign gate and Registry go-live. SCOUT can be asked for an outside review.
WHAT CHANGED TODAY (Oct 19, afternoon)
- Multi-tenancy designed in (G30). Every audit event, Registry allowlist, policy, approval and cap now carries a tenant ID; cross-tenant reads, writes and approval reuse are blocked in the prototype (mock tenants, synthetic data).
- Gateway bypass fixed (G32). The results store now accepts only a gateway-signed, single-use credential tied to an approved request.
- Tests independently re-run and signed. Pam re-ran the full suite herself: 74/74 pass, no mismatches. I signed it. G30, G32 and the gateway-side fail-closed fix are closed.
- Console decided (G31), per Pam's plan. The Pilot gets only a minimal approver screen. No UI in Phase 3; the Registry stays config-as-code. The full console comes in Phase 5, tenant admin in Phase 4, evidence-pack export in Phase 6. UI stays minimal; there is no front-end owner.
- I am the sole Pilot write approver. No bot approves a write; Pam witnesses and logs only. Ed is updating the files and will re-run the tests.
- Clef replaces Jev (G33). Cloudflare Workers AI Clef is the bounded-judgment check at the Guard step; Jev stays benchmark-only. It never replaces human approval for writes. I approved a live Clef test capped at $10, enforced in code; the token is pending.
YOUR INPUT NEEDED: FLAG BY FRI OCT 23
| # | Item | Owner | Proposed answer |
|---|
| 1 | Pilot document count | Pam; Jon picks | UNKNOWN. Needed before Pilot entry Nov 3 |
| 2 | Is Fri Nov 27 a Scale holiday? | Jon | UNKNOWN. Pilot is 19 working days, 18 if off |
| 3 | Which approver screen for the Pilot | Ed + Pam | LiteLLM's built-in UI if it can carry our approval records (untested); otherwise a thin single page. Decide by Nov 2 |
| 4 | How client users map to a tenant (Entra tenant, guest, or Okta) | Ed; Jon (identity) | UNKNOWN. Decide in Assess |
| 5 | Go-live tenant (lab vs Azure/AWS) and Entra ID confirmation | Jon; Ed | Entra ID assumed; tenant UNKNOWN. Due Nov 2 |
| 6 | Production gateway identity: mTLS and/or gateway-signed token | Ed | UNKNOWN. Options listed; none tested |
Full list: open-items-for-team.md in the AI*Right workspace.
HOW WE'LL COMMUNICATE
- Weekly status email every Monday by 9:00 AM ET: progress against plan, red/amber/green, blockers, next week's focus, updated dates.
- Phase gate review at the end of each phase: a one-page summary plus the decision needed.
- Ad hoc messages only for high-risk blockers or decisions.
WHAT I NEED FROM YOU
Flag any concern with the dates, and your answers to the table above, by Fri Oct 23.
Jon