Every agent in a multi-agent Azure solution must emit structured logs, enforce the caller’s authorization before tool calls, and translate certain tool exceptions into user-safe messages. The team wants these capabilities applied consistently without duplicating code inside each agent’s prompt or business logic. What should they design?
Select an answer to reveal the explanation.
Short Explanation
Cross-cutting concerns belong in middleware or shared pipeline hooks—logging, authz checks before tools, and safe exception translation—so every agent gets the same behavior without copy-paste. Natural-language-only instructions in prompts are not reliable enforcement. Portal screenshots are not observability. Disabling controls for latency is a security and ops anti-pattern. A is the reusable design.
Full Explanation
Correct answer: A. Multi-agent solutions should design middleware for reusable capabilities—including logging, authorization, and exception handling—applied consistently across the solution rather than reimplemented per agent.
B is incorrect because prompt text is not a dependable enforcement mechanism for authorization or structured logging.
C is incorrect because manual portal screenshots do not provide automated structured observability.
D is incorrect because removing logging and authorization trades safety and operability for latency and is not an acceptable default.
Exam focus: middleware centralizes cross-cutting multi-agent concerns.