Microsoft AI-500 : Designing and Implementing Multi-Agent AI Solutions

You have a Microsoft Agent Framework workflow processor that receives customer support requests from a queue. Each request is evaluated by three independent Microsoft Foundry agents.
You discover that the current processor dequeues 30 requests at a time and starts all agent runs immediately.
During peak load, as many as 90 agent runs execute simultaneously, and the downstream API receives partial participant messages.
A single agent run completes in five seconds at the 95th percentile (95p), and the target throughput is 120 requests per minute.
You need to change the orchestration to ensure that it meets the throughput target and prevents more than 30 agent runs from executing simultaneously. The solution must produce one consolidated downstream payload for each request.
What should you do?

• A. Dequeue 10 requests per batch. Start 10 group chat workflows that include the three agents and a manager.
• B. Dequeue 30 requests per batch. Start a single ConcurrentBuilder workflow that includes 90 agent executors as participants.
• C. Dequeue 10 requests per batch. Start 10 sequential workflows that include the three agents as ordered steps.
• D. Dequeue 10 requests per batch. Start 10 ConcurrentBuilder workflows that include the three agents as participants.

You have a Microsoft Foundry agent that answers questions about products. You evaluate the agent responses and discover the following issues:
* Questions about a product named product1 make up 40 percent of user traffic, and responses are returned in inconsistent formats.
* Questions about a product named product2 appear infrequently in the existing logs but have high escalation rates.
The available chat logs include customer names and contact details, and the labeling budget enables subject matter experts (SMEs) to review only a limited subset of training examples.
You need to design a dataset preparation plan to fine-tune the agent. The solution must meet the following requirements:
* Match usage patterns for the product1 questions.
* Cover the product2 questions.
* Meet General Data Protection Regulation < GDPR) and Health Insurance Portability and Accountability Act (HIPAA) privacy requirements for names and contact details.
* Minimize SME review efforts during labeling.
What should you include in the design? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.

You have a Microsoft Foundry multi-agent customer support solution. The solution includes a triage agent that uses Azure Al Search to retrieve customer-supplied HTML articles and Azure Functions to retrieve customer relationship management (CRM) case records. A custom guardrail is assigned directly to the agent.
Some retrieved HTML articles contain hidden instructions that attempt to override the triage agent ' s system message You need to configure guardrails to meet the following requirements:
* Evaluate the complete payload from the supported tools before the content is available to the agent.
* Prevent malicious instructions embedded in externally retrieved content from influencing the agent
* Stop processing when tainted data is detected and inform the security team.
What should you configure? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.

You have a Microsoft Foundry multi-agent solution for loan applications. Each agent scores a full application independently and does NOT require output from other agents.
You need to recommend an orchestration pattern that meets the following requirements:
Produces one aggregated recommendation
Preserves independent scoring -
Minimizes end-to-end latency -
Minimize development effort -
What should you recommend?

• A. sequential
• B. magnetic
• C. group chat
• D. concurrent

You have a Microsoft Foundry project that processes customer requests through several stages: A routing agent receives investigation requests, delegates calculations to a data analysis agent that can use Code Interpreter, and delegates source-grounded summaries to a literature review agent.
You discover the following issues:
* Tasks are sometimes routed to the incorrect agent.
* The format of the final response is inconsistent.
You need to ensure that compound requests are routed consistently, and the final response is in a consistent format. The solution must meet the following requirements:
* Minimize changes to the application code.
* Apply to every future conversation handled by the agents.
* Clarify the expected behavior for representative compound inputs.
Which prompt design should you implement?

• A. Add repository-wide constraints that list approved agent names, tool names, and response rules.
• B. Add system level role instructions that define agent domains, task boundaries, and response objectives.
• C. Add per request prompt cues that provide JSON openers, section labels, and final-answer prefixes.
• D. Add few-shot instruction examples that cover routing decisions and schema-compliant final outputs.