Two business units already run production agents—one on Microsoft Agent Framework in Foundry and one on an external LangGraph service. You must compose them into a single customer journey without rewriting both codebases or sharing long-lived static secrets in prompts. What is the best integration approach?
Select an answer to reveal the explanation.
Short Explanation
Answer C. The blueprint calls out integrating existing agents into a multi-agent solution securely with Agent2Agent (A2A) and/or MCP. That preserves investments, standardizes contracts, and allows identity-scoped auth instead of prompt-embedded secrets. Mega-prompts discard operational boundaries. Unauthenticated GETs with keys in URLs are insecure. Manual copy-paste is not a production integration.
Full Explanation
Correct answer: C. Secure composition of heterogeneous agents is an explicit develop skill: use A2A and/or MCP so Foundry and external LangGraph agents interoperate through authenticated, versioned interfaces. Each agent keeps its own runtime while the orchestrator discovers capabilities and invokes them under least-privilege identities.
A is incorrect: collapsing into one prompt loses independent scaling, ownership, evaluation, and security boundaries.
B is incorrect: unauthenticated or query-string key patterns leak credentials and fail Zero Trust expectations for multi-agent production systems.
D is incorrect: human swivel-chair integration is not automatable orchestration and breaks SLA and audit requirements.
Design middleware for logging, authorization, and exception handling across the A2A/MCP boundary.