Play 02
AI Landing Zone
Foundational Azure infrastructure for AI workloads — networking, identity, governance.
Deploy the foundational infrastructure every AI workload needs. VNet with private endpoints keeps traffic off the public internet, Managed Identity eliminates secrets, RBAC locks down access, and Key Vault stores what must be stored. This is Play 0 — run it before anything else.
Architecture Pattern
Hub-spoke landing zone, private endpoints, RBAC governance
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Landing Zone Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (161 lines), evaluate (170 lines), tune (227 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with subscription input + envFile
TuneKit (AI Config)
- config/landing-zone.json — VNet CIDR, subnets, SKUs, GPU quota
- infra/main.bicep — full Bicep template
- infra/parameters.json — region, environment, GPU toggle
Tuning Parameters
Machine evidence
FrootAI evidence lifecycle
This is an internal evidence maturity label, not third-party certification, accreditation, legal compliance, or a production guarantee. Missing or expired evidence demotes automatically; catalog claims cannot promote a play.
This play currently has design evidence only. A runnable scenario, endpoint evaluation, and build receipts are the next contiguous gates.
Repo Intelligence
v1A no-clone, revision-pinned map for agents and humans. Observed evidence is separated from inferred flow so the output stays useful without pretending to be a full call graph.