AI Executive Office — CXO Assistant Platform  ·  View 02 of 30  ·  1 · Context and scope

High-Level Architecture

The shape of the platform in one picture: six stages from an executive's question to a governed action.

Editable source SVG draw.io All views
Executive experience Teams app brief · approvals Executive web Container Apps Mobile Intune managed Edge and identity Front Door + WAF TLS · DDoS API Management tenant quota Entra ID OBO · CA policy Orchestration and decision Executive Orchestrator AI Foundry Agent Service Specialist agents 10 capability packs Decision engine situation to option set Investigation runs Durable Functions Grounding and action Tool plane typed · OBO only AI Search hybrid · ACL trimmed Semantic model the only KPI source ML endpoints forecast · anomaly Execution plane Logic Apps Standard Data and knowledge OneLake lakehouse bronze · silver · gold Fabric warehouse canonical model Entity graph Cosmos DB Gremlin Eventstream CDC · signals Decision store Azure SQL · append-only Enterprise systems ERP and finance Procurement Projects Document estate approved write CDC outcome check AI Executive Office — High-Level Architecture Application we own Interface / broker Security / platform Data store Queue / topic External / third party synchronous event / async batch The model never reaches a system of record. Every arrow into the right-hand column is a typed tool or an approved action. v 1.0 · owner Data & AI Global Practice · date 2026-09

The load-bearing decision

  • The language model sits in the orchestration stage and nowhere else. It never appears in the data stage, and it holds no credential for any store — everything it learns arrives through the tool plane, carrying the caller's identity
  • Reads fan out widely; writes converge on a single execution plane. That asymmetry is the whole governance model, and it is why the right-hand column has one solid arrow into it and many dotted ones out

Deliberate omissions

  • Guardrails, evaluation and audit are on every path but drawn only once, in view 29. Repeating them here would triple the arrows and say nothing new
  • The detection pipeline that produces the morning brief runs beside this flow rather than inside it — view 18

Numbers

  • Simple KPI question: p95 under 5 seconds, two model calls
  • Cross-system investigation: asynchronous, 30–180 seconds, progressively disclosed rather than made to wait
  • Morning brief: generated by 06:30 local, delivered 07:10