You have a Microsoft Foundry multi-agent solution that routes requests from an intake agent to a retrieval agent, and then to a resolution agent. The retrieval agent uses a knowledge search tool.
Security testing reveals the following recurring issues:
* Some users submit jailbreak-style prompts at the start of a conversation.
* Some retrieved documents contain hidden instructions intended to manipulate the downstream agent The legal department at your company requires that final responses be flagged for review if they contain protected text. You need to configure guardrails to resolve the security issues and meet the legal requirements.
What should you configure?

• A. * User input attacks at User input set to Block
  * Indirect attack at Tool call set to Block
  * Protected material for text at Output set to Block
• B. * User input attacks at User input set to Annotate and block
  * Indirect attack at Tool response and Action set to Annotate and block
  * Protected material for text at Output set to Annotate only
• C. * User output attacks at User output set to Annotate and block
  * Indirect attack at Tool response set to Annotate and block
  * Protected material for text at Output set to Annotate and block

You need to modify claim Approval to prevent the prompt injection issue. Which guardrail should you use?

• A. Prompt shields for user prompts
• B. Prompt shields for documents
• C. Groundedness detection
• D. Task Adherence

You have a Microsoft Foundry multi-agent customer support solution that routes requests from an intake agent to a retrieval agent, and then to a resolution agent. A custom guardrail is assigned to the agents.
You discover that some legitimate support requests are blocked, and some injected instructions in retrieved documents are allowed.
You need to validate the updated guardrail. The solution must meet the following requirements:
* Identify false positives and false negatives.
* Verify policy coverage across the agent solution
* Prevent changing the production agent behavior during testing
* Measure intervention accuracy by using a control and intervention point.
What should you do?

• A. Run labeled benign and adversarial test cases through each workflow path and evaluate the results from annotations and logs.
• B. Review the Guardrails tab in the Compliance workspace, export deployment configurations, and mark each deployment as Compliant or Noncompliant
• C. Test a small set of jailbreak prompts by using Try in Playground Review the displayed risk messages and tune the highest-triggered categories.
• D. Update the guardrail to annotate-only mode, collect live user interactions, and summarize blocked and annotated events after rollout

You have a single-agent customer support copilot built by using Microsoft Foundry. The application that hosts the copilot runs on multiple stateless instances, and rolling upgrades restart the instances.
[Architect multi-agent solutions]
Customer investigations can last for several days. A user can have multiple unrelated investigations, and stable user preferences, such as a preferred contact method, must be available across sessions and devices Compliance reporting requires a one-year, queryable audit trail of thread messages and session metadata.
During long investigations, the model context window regularly approaches its limits. Temporary tool traces do NOT affect final outcomes after the run completes.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.

You have a Microsoft Foundry resource that hosts Azure OpenAI model deployments for three projects. Each project is for a different business unit. The projects share the same Foundry resource.
You need to implement a Microsoft Cost Management view that separates the shared model spend by the project The solution must meet the following requirements:
* Use cost data that can be reconciled by using Azure Cost Management.
* Minimize manual tagging.
What should you use?

• A. cost analysis scoped to the resource group with grouping by Meter and exports for each project
• B. cost analysis scoped to the Foundry resource with a tag filter on project
• C. cost analysis scoped to the subscription with a Service tier: Azure OpenAI filter and budgets for each business unit
• D. cost analysis scoped to the Foundry resource with grouping by Resource and saved views for each project