Confidently Practice Online with Free AI-500 Exam Cram

You need to implement an advanced prompt engineering strategy to resolve the Patient Intake agent issues.The solution must prevent hardcoding new logic into the agent ' s core prompt.What should you do?

You have a Microsoft Foundry project that includes three agents named FinanceOrehestrator,invoiceValidationAgent, and PayaentApprovalAgent. The agents interact with an external agent namedvendorfiegotiationAgent. The agents are configured as shown in the following table.You need to recommend an identity structure for the agents.What should you recommend? To answer, select the appropriate options in the answer area.NOTE: Each correct selection is worth one point.Please review the explanation below to find the correct answer.Do you know the answer?

You have a multi-agent Retrieval-Augmented Generation (RAG) solution that uses a Foundry IQ knowledgebase. The solution includes a support agent and a policy agent.You have an evaluation dataset that contains the following for each user query• The expected source IDs• Retrieved chunks in rank order• The final agent responseYou discover that an embedding model change and a custom analyzer change cause the failed traces shown inthe following table.You need to isolate the failing parts of the RAG pipeline.Which evaluator should you use for each agent? To answer, drag the appropriate evaluators to the correctagents. Each evaluator may be used once, more than once, or not at all. You may need to drag the split barbetween panes or scroll to view contentNOTE: Each correct selection is worth one point.Please review the explanation below to find the correct answer.Do you know the answer?

You have a Microsoft Agent Framework multi-agent workflow. The workflow includes a context providerthat injects a condensed memory summary into each agent invocation. Requirements and acceptance criteriaare stored in GitHub issues.During a long-running workflow, the acceptance criteria changes. Later agents sometimes apply the earliercriteria. Token telemetry shows condensed summaries grow across handoffs. causing older content to betruncated.You need to ensure that the later agents use the current requirements. The solution must limit context windowgrowth.What should you do?

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