What problem does it solve? AI agents need distinct, auditable identities with independently scoped permissions, but provisioning Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities through Microsoft Graph involves non-obvious object models, typed endpoints, and a two-step fmi_path token exchange that is easy to misconfigure. ## Core Features & Use Cases - Identity Provisioning: Create Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph with correct sponsors, credentials, and permission grants. - Runtime Token Exchange: Implement the two-step fmi_path exchange for autonomous and OBO flows, including cross-tenant scenarios and Managed Identity + Workload Identity Federation. - Polyglot Sidecar Deployment: Deploy the Microsoft Entra SDK for AgentID sidecar container so Python, Node, Go, and Java agents acquire tokens over HTTP without embedding SDKs. - Use Case: You are building a multi-tenant AI agent platform where each agent instance needs its own identity and audit trail. Use this Skill to provision the Blueprint hierarchy, grant per-agent Graph permissions, and wire up OBO token exchange. ## Quick Start Ask the AI to create an Agent Identity Blueprint and BlueprintPrincipal in your tenant, then create a per-instance Agent Identity and show the fmi_path token exchange code.
