APEX
Agentic Platform Engineering eXperience for Azure.
APEX turns Azure platform engineering requirements and live subscription evidence into
Well-Architected assessments, evidence-backed cost reports, and deployable Bicep or Terraform
in VS Code with GitHub Copilot.
Two ways to use APEX
1. Infrastructure delivery workflow
01-Orchestrator coordinates specialized agents and subagents across Requirements, Architecture
and Cost, Optional Design, Governance, IaC Planning, Bicep or Terraform Code Generation,
Deployment, and As-Built Documentation. Independent challenger-review-subagent checks and human
approval gates govern each stage before changes advance.
Early Architecture can start against shared Azure Landing Zones Corp policy assumptions under
corp-policy-v1, while IaC planning completion, code generation, and deployment require
target-verified private policy capture. Cost estimates pair workload SKUs with evidence-backed
retail pricing from Azure MCP. Read the workflow overview.
2. Standalone WAF assessment
Run /waf-assess-existing in 01-Orchestrator in evidence_only or requirements_led mode
against read-only Azure subscriptions, local IaC and diagrams, or both. The assessment generates
a five-pillar Well-Architected report, existing-state SVG and PNG diagrams, Azure Cost
Management analysis with visual charts, and a prioritized Excel and Markdown action register.
Independent quality reviews run before final bundle acceptance. Read the
WAF assessment guide.
Start here
For new Azure delivery or assessment projects, start from the Accelerator template rather than
cloning this upstream repository:
- Create a private repository from the
Accelerator template.
- Clone the new repository to the host machine. Microsoft employees must exit all VS Code
windows and run
.devcontainer/open-microsoft.ps1 on Windows or
bash .devcontainer/open-microsoft.sh on Linux, macOS, and WSL before starting the
container. Read Package Sources for host feed
setup. Everyone else can run code ..
- Reopen the folder in the dev container and follow the
quickstart guide.
To contribute to APEX, read AGENTS.md for local setup, repository conventions, and
the npm run validate:all validation suite, plus the
contributing guide.
Delivery workflow
%%{init: {'theme':'neutral'}}%%
sequenceDiagram
autonumber
participant U as User
participant C as Orchestrator
participant R as Requirements
participant X as Challenger
participant A as Architect
participant G as Governance
participant IaC as IaC Plan
participant Gen as IaC Code
participant D as Deploy
participant W as As-Built
Note over C: ORCHESTRATION LAYER<br/>AI prepares. Humans decide.
U->>C: Describe infrastructure intent
C->>R: Translate intent into structured requirements
R-->>C: 01-requirements.md (includes iac_tool selection)
C->>X: Challenge requirements
X-->>C: challenge-findings-requirements.json
C->>U: Present requirements + challenge findings
rect rgba(255, 200, 0, 0.15)
Note over U,C: HUMAN APPROVAL GATE
U-->>C: Approve requirements
end
C->>A: Assess architecture (WAF + Cost)
Note right of A: cost-estimate-subagent<br/>handles pricing queries
A-->>C: 02-architecture-assessment.md + 03-des-cost-estimate.md
C->>X: Challenge architecture
X-->>C: challenge-findings-architecture.json
C->>X: Independently review cost feasibility
X-->>C: challenge-findings-cost-estimate.json
C->>U: Present architecture + challenge findings
rect rgba(255, 200, 0, 0.15)
Note over U,C: HUMAN APPROVAL GATE
U-->>C: Approve architecture
end
C->>G: Discover policy constraints
G-->>C: 04-governance-constraints.json and Markdown
C->>X: Reconcile constraints with approved architecture
X-->>C: challenge-findings-governance-constraints-pass1.json
C->>U: Review governance constraints and confirmations
U-->>C: Approve governance
C->>IaC: Create implementation plan using approved inputs
Note right of IaC: Unified IaC Planner (05)<br/>routes based on decisions.iac_tool
IaC-->>C: 04-implementation-plan.md
C->>X: Challenge implementation plan
X-->>C: challenge-findings-plan.json
C->>U: Present plan + challenge findings
rect rgba(255, 200, 0, 0.15)
Note over U,C: HUMAN APPROVAL GATE
U-->>C: Approve plan
end
C->>Gen: Generate IaC templates (AVM-first)
Note right of Gen: Bicep codegen or Terraform codegen
Gen-->>C: infra/bicep/{project} or infra/terraform/{project}
rect rgba(0, 150, 255, 0.08)
Note over C,Gen: Validation loop
alt Validation passes
C->>U: Present templates for deployment
rect rgba(255, 200, 0, 0.15)
Note over U,C: HUMAN APPROVAL GATE
U-->>C: Approve for deployment
end
else Validation fails
C->>Gen: Revise with feedback
end
end
C->>D: Execute deployment
Note right of D: what-if or terraform plan preview first
D-->>C: 06-deployment-summary.md
C->>U: Present deployment summary
rect rgba(255, 200, 0, 0.15)
Note over U,D: HUMAN VERIFICATION
U-->>C: Verify deployment
end
C->>W: Generate workload documentation
Note right of W: Reads prior artifacts and deployed resource state
W-->>C: 07-*.md documentation suite
C->>U: Present as-built docs
Note over U,W: AI orchestrated. Human governed. Azure ready.
What this repository contains
- Specialized agents, subagents, skills, and instruction files for VS Code Copilot
- Reference implementations for Azure Verified Modules in Bicep and Terraform
apex-recall CLI for project session state, step transitions, and review gates
- Validation scripts, MCP configuration, artifact templates, and Architecture Explorer graph metadata
See CHANGELOG.md for release history.
License
MIT
评论