Physician Approval for ER Triage in Lead Orchestrator Workflow
Implement multi-agent orchestration
Design and implement guardrails for multi-agent solutions
Short answer
B Add an Ask a question node in the Lead Orchestrator workflow so triage assessments recommending an emergency room visit pause for physician approval before continuing.
Question
This is a case study. Case studies are not timed separately. You can use as much exam time as you would like to complete each case. However, there may be additional case studies and sections on this exam. You must manage your time to ensure that you are able to complete all questions included on this exam in the time provided.
To answer the questions included in a case study, you will need to reference information that is provided in the case study. Case studies might contain exhibits and other resources that provide more information about the scenario that is described in the case study. Each question is independent of the other questions in this case study.
At the end of this case study, a review screen will appear. This screen allows you to review your answers and to make changes before you move to the next section of the exam. After you begin a new section, you cannot return to this section.
To start the case study
To display the first question in this case study, click the Next button. Use the buttons in the left pane to explore the content of the case study before you answer the questions. Clicking these buttons displays information such as business requirements, existing environment, and problem statements. If the case study has an All Information tab, note that the information displayed is identical to the information displayed on the subsequent tabs. When you are ready to answer a question, click the Question button to return to the question.
Overview
Contoso, Ltd. is a health provider. The company is building an Azure-based multi-agent solution to streamline patient triage, access historical medical records, and schedule specialist appointments.
Existing Environment
Microsoft Foundry
Contoso has a Microsoft Foundry project named HealthAssist that contains the following agents:
Patient Intake: A public-facing chat interface where patients describe their symptoms
Record Retrieval: An internal system that retrieves a patient's past medical history from a secure database
Scheduling: Integrates with an external third-party booking system by using a Model Context Protocol (MCP) server
Lead Orchestrator: A workflow agent that makes decisions based on the output of the other agents
Knowledge Base
Contoso uses a Retrieval-Augmented Generation (RAG) system that contains clinical documents. Only the Patient Intake agent can access the RAG system.
Problem Statements
Contoso identifies the following issues:
The MCP server used by the Scheduling agent frequently times out during peak load.
Patients report that during the intake process, the session frequently times out silently without indicating why. The issue occurs during workflow execution.
Occasionally, the Patient Intake agent cannot extract relevant symptoms when patients provide verbose personal stories that are irrelevant to the medical issue.
When the Patient Intake agent engages in long, multi-turn conversations with patients, the accumulating conversation history causes high latency due to massive prompt sizes and risks that exceed the model's context window.
Requirements
Business Requirements
Contoso identifies the following business requirements:
A physician must approve any triage assessments that recommend an emergency room visit.
HealthAssist must be able to handle large spikes in concurrent patient intake requests during flu season.
Before releasing updates to HealthAssist, the clinical team must review the accuracy of the Lead Orchestrator agent triage routing decisions against a set of historical test cases.
Safety Requirement
Contoso identifies the following safety requirements:
Implement a robust guardrail strategy to prevent HealthAssist from providing inappropriate medical diagnoses.
Ensure that all public-facing agents block violence and hate speech.
Prevent hardcoding new logic into the agents' core prompt.
Consultant Proposal
A consulting firm proposes the following solution to address various requirements and issues:
Add a guardrail that has the highest sensitivity for all controls.
Add a system prompt message to direct the agent to ignore hate speech.
Implement a short-term memory context window that prompts patients multiple times to verify their symptoms.
Add a system prompt message to direct the agent to recommend an emergency room visit if the patient is having heart palpitations.
Security Requirements
Contoso identifies the following security requirements:
Ensure that the agents do NOT have overlapping permissions to prevent lateral movement.
Prevent the agents from accessing patients' data outside of the current patient context.
Ensure that all API keys are securely stored and rotated.
Follow the principle of least privilege, when possible.
Performance Requirements
Contoso identifies the following performance requirements:
Token usage must be monitored.
Long-term semantic memory must be isolated by patient.
You need to define a strategy to meet the business requirements for emergency room visits.
Which workflow node should you add to the Lead Orchestrator workflow?
To answer the questions included in a case study, you will need to reference information that is provided in the case study. Case studies might contain exhibits and other resources that provide more information about the scenario that is described in the case study. Each question is independent of the other questions in this case study.
At the end of this case study, a review screen will appear. This screen allows you to review your answers and to make changes before you move to the next section of the exam. After you begin a new section, you cannot return to this section.
To start the case study
To display the first question in this case study, click the Next button. Use the buttons in the left pane to explore the content of the case study before you answer the questions. Clicking these buttons displays information such as business requirements, existing environment, and problem statements. If the case study has an All Information tab, note that the information displayed is identical to the information displayed on the subsequent tabs. When you are ready to answer a question, click the Question button to return to the question.
Overview
Contoso, Ltd. is a health provider. The company is building an Azure-based multi-agent solution to streamline patient triage, access historical medical records, and schedule specialist appointments.
Existing Environment
Microsoft Foundry
Contoso has a Microsoft Foundry project named HealthAssist that contains the following agents:
Patient Intake: A public-facing chat interface where patients describe their symptoms
Record Retrieval: An internal system that retrieves a patient's past medical history from a secure database
Scheduling: Integrates with an external third-party booking system by using a Model Context Protocol (MCP) server
Lead Orchestrator: A workflow agent that makes decisions based on the output of the other agents
Knowledge Base
Contoso uses a Retrieval-Augmented Generation (RAG) system that contains clinical documents. Only the Patient Intake agent can access the RAG system.
Problem Statements
Contoso identifies the following issues:
The MCP server used by the Scheduling agent frequently times out during peak load.
Patients report that during the intake process, the session frequently times out silently without indicating why. The issue occurs during workflow execution.
Occasionally, the Patient Intake agent cannot extract relevant symptoms when patients provide verbose personal stories that are irrelevant to the medical issue.
When the Patient Intake agent engages in long, multi-turn conversations with patients, the accumulating conversation history causes high latency due to massive prompt sizes and risks that exceed the model's context window.
Requirements
Business Requirements
Contoso identifies the following business requirements:
A physician must approve any triage assessments that recommend an emergency room visit.
HealthAssist must be able to handle large spikes in concurrent patient intake requests during flu season.
Before releasing updates to HealthAssist, the clinical team must review the accuracy of the Lead Orchestrator agent triage routing decisions against a set of historical test cases.
Safety Requirement
Contoso identifies the following safety requirements:
Implement a robust guardrail strategy to prevent HealthAssist from providing inappropriate medical diagnoses.
Ensure that all public-facing agents block violence and hate speech.
Prevent hardcoding new logic into the agents' core prompt.
Consultant Proposal
A consulting firm proposes the following solution to address various requirements and issues:
Add a guardrail that has the highest sensitivity for all controls.
Add a system prompt message to direct the agent to ignore hate speech.
Implement a short-term memory context window that prompts patients multiple times to verify their symptoms.
Add a system prompt message to direct the agent to recommend an emergency room visit if the patient is having heart palpitations.
Security Requirements
Contoso identifies the following security requirements:
Ensure that the agents do NOT have overlapping permissions to prevent lateral movement.
Prevent the agents from accessing patients' data outside of the current patient context.
Ensure that all API keys are securely stored and rotated.
Follow the principle of least privilege, when possible.
Performance Requirements
Contoso identifies the following performance requirements:
Token usage must be monitored.
Long-term semantic memory must be isolated by patient.
You need to define a strategy to meet the business requirements for emergency room visits.
Which workflow node should you add to the Lead Orchestrator workflow?
Key Takeaways
The tested concept is selecting the correct Foundry workflow node to implement human-in-the-loop physician approval; the common trap is confusing Ask a question with Deliver a message or an Agent node, neither of which can halt the workflow for a required human decision.
Contoso's Lead Orchestrator must route any emergency-room triage assessment to a physician for approval, which requires a human-in-the-loop step in the agent workflow. In Microsoft Foundry agent workflows, the Ask a question node pauses workflow execution and returns control so a human reviewer can respond, making it the correct choice for physician sign-off.
Common mistake: Learners most often pick A (Deliver a message), assuming the workflow can simply notify the physician, but a message node only emits output text and does not pause the workflow or capture the physician's approval decision before triage proceeds.
Expert Analysis
Why the Answer Is Correct
The business requirement states that a physician must approve any triage assessment recommending an emergency room visit, so the Lead Orchestrator workflow needs a node that suspends execution and returns to the caller to obtain a human response. In Microsoft Foundry agent workflows, the Ask a question node is exactly the human-in-the-loop mechanism: it stops the workflow, prompts a reviewer (the physician), and resumes once the answer is supplied. That paused-and-awaiting-response behavior is what enforces the approval gate before an ER recommendation can be finalized. This also aligns with the consulting firm's flawed proposal to hardcode ER logic in the system prompt, which the safety requirement forbids.Why the Other Options Are Wrong
A. Deliver a message only streams or emits text to the conversation; it cannot pause workflow execution, so the workflow would continue without any physician approval. C. Agent invokes another AI agent, which would add an automated model step rather than a human decision-maker, and the requirement explicitly calls for a physician, not another agent. D. Go to is a branch/redirect control that moves execution to another node, which changes flow but does not create any approval checkpoint for a human reviewer.Community Comment Notes
A commenter supporting option B explained that "The Ask a question node enables human-in-the-loop approval, allowing a physician to approve emergency room recommendations," which matches Foundry's documented behavior of returning control to the caller when this node executes. No community comments argued for any other node, and the case study's other consultant proposals (highest-sensitivity guardrails, a system prompt telling the agent to ignore hate speech, and hardcoded ER recommendations) violate the safety requirement to prevent hardcoding logic into prompts, reinforcing that a workflow-level human approval node is the intended answer.Official Reference
https://learn.microsoft.com/en-us/azure/ai-foundry/agents/workflows
This link opens the official vendor documentation in a new tab.
Exam Strategy
When a requirement says a specific human role must approve or review a decision, look for the Foundry workflow node that pauses execution and returns a response — that is the Ask a question node. Reject any option that only sends output (message) or only redirects flow (go to), because neither creates an approval gate.
Frequently Asked Questions
Why can't a Deliver a message node satisfy the physician approval requirement?
A message node only outputs text to the conversation and never pauses execution, so the workflow would proceed without any physician decision being captured or enforced.
How does Ask a question differ from adding an ER recommendation to the system prompt?
Hardcoding ER rules in the prompt violates the safety requirement to keep logic out of core prompts; the Ask a question node enforces approval dynamically at the workflow level through human-in-the-loop review.
Discussion 1 contributions
Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.
From public community threads 1
-
modalityware 👍 1 Answered BThe Ask a question node enables human-in-the-loop approval, allowing a physician to approve emergency room recommendations.
Reader comments & corrections
No reader corrections yet — spotted an error or have a note? Share it below.