AI Agent Orchestration Platform

Solution Architecture v1.0 · Data & AI Global Practice · 2026-08 · 32 views · Microsoft Azure

A centralised runtime and control plane for designing, deploying, orchestrating, observing and governing AI agents and multi-agent workflows on Azure. Eight decisions carry the design: the control plane and the execution plane are separated absolutely, and the interface between them is a signed immutable bundle rather than a shared database; durable execution runs on Azure Durable Functions behind a workflow-engine port, so the engine can be replaced without touching agent code; every model call goes through API Management as an AI gateway, so metering, token limits, semantic caching, circuit breaking and provider fallback are policy rather than application code; tools are out-of-process and least-privileged, with credentials brokered per call and code execution confined to Hyper-V isolated session sandboxes; policy is authored centrally as signed Rego bundles and evaluated locally in every worker, so a control-plane outage cannot make policies fail open; delivery is at-least-once with idempotency pushed to the handler; memory is four stores rather than one, each permission-filtered and audited; and budget is reserved at admission, so a run cannot start that it cannot afford to finish.

32 views 32 HTML views32 SVG32 draw.io Updated 2026-08-31
Architecture views

32 views, each in three formats.

Open a view to read it in full. Every SVG carries its diagram source inside it, so it opens in diagrams.net fully editable with no import step; the draw.io files are the same diagrams as plain source.

  1. 01
    System Context

    Who uses the platform, what it depends on, and where the boundary is drawn.

  2. 02
    High-Level Architecture

    The shape of the platform in one picture, for the reader who will see only one.

  3. 03
    Control Plane and Execution Plane

    The one architectural boundary that everything else on this site depends on.

  4. 04
    Layered Architecture

    What depends on what, and the single dependency that points the wrong way.

  5. 05
    Container and Component Architecture

    The deployable units, their technology, their replica ranges and the Azure service each one owns.

  6. 06
    Integration and Interface Catalogue

    Every way something enters or leaves the platform, with protocol, direction and cadence.

  7. 07
    Agent Runtime Internals

    What one worker does between leasing a step and committing it, and where the controls sit.

  8. 08
    Model Abstraction and Routing

    How a request for a capability becomes a call to a specific model, and what happens when that model is unavailable.

  9. 09
    Tool Plane and Permissions

    How each class of tool is discovered, authorised, invoked, validated and recorded.

  10. 10
    Event and Messaging Topology

    Which queues and topics exist, why there are several, and how a stuck message reaches a human.

  11. 11
    Definition Lifecycle and Versioning

    How an agent, workflow, prompt, tool or policy definition becomes an immutable published version.

  12. 12
    Data Architecture and Storage Zones

    What is authoritative, what is rebuildable, what is large, and what disaster recovery actually has to cover.

  13. 13
    Memory Subsystem

    Six kinds of memory, where each lives, how it is retrieved, who may read it and how long it survives.

  14. 14
    Context Management

    How one model invocation's context window is assembled, compressed, protected and accounted for.

  15. 15
    Data Flow by Data Class

    Six classes of data, each traced from where it is produced to where it finally rests.

  16. 16
    Platform Data Model

    The entities a governance question actually reads: who ran what, on which version, with whose approval, at what cost.

  17. 17
    Execute an Agent

    One synchronous run end to end, including the tool hop and the point at which the result becomes final.

  18. 18
    Multi-Agent Coordination

    Six coordination patterns, and the claim that all six are workflow definitions rather than different platforms.

  19. 19
    Durable Execution and Replay

    What survives a crash, how failure is classified, and where a run goes when recovery is exhausted.

  20. 20
    Human-in-the-Loop

    How a run suspends for a human decision, and what happens when nobody answers.

  21. 21
    Safety Guardrails

    Six threat classes, and what the platform does about each at detect, decide, act and record.

  22. 22
    Policy and Budget Enforcement

    Five policy scopes against five decision points: exactly what is evaluated, and where.

  23. 23
    Deployment Topology

    What runs where, what is redundant, and what a region loss actually costs.

  24. 24
    CI/CD and Environment Promotion

    How a change reaches production, and what stops a bad one at each hop.

  25. 25
    Observability and Tracing

    Six signal types across emit, collect, store, consume and act — and the identifier that joins them.

  26. 26
    Cost Management and Attribution

    How every token and tool call is metered, attributed, capped and then made cheaper.

  27. 27
    Evaluation and Quality

    The loop from production failure back to a better agent version, and the gate that closes it.

  28. 28
    Security Zones and Trust Boundaries

    Where an attacker arrives, what stops them at each boundary, and what an agent is trusted to do.

  29. 29
    Identity and Delegation

    The path from a user signing in to a tool credential, and what is deliberately not passed along it.

  30. 30
    Multi-Tenant Isolation

    Four layers of isolation, what each one actually prevents, and what the pooled tier still accepts.

  31. 31
    Failure Modes and Residual Risk

    Eight ways this platform fails, what detects each, what contains it, and what is left over.

  32. 32
    Delivery Roadmap

    What is built first, what waits, and which items are prerequisites rather than enhancements.

The package

Everything as it was delivered.

These files are served exactly as they were produced — the diagram pages keep their own house style because that is the artifact, not a rendering of it.