Microsoft AI-103 Exam Dumps - Actual Questions Answers

The correct recommendation is B. Add a connection to the Azure AI Search resource . Microsoft Foundry project connections are used to centrally define access from a project to external resources, including Azure AI Search. The official connection guidance states that you can add a connection by selecting an external service such as Azure AI Search , choosing the resource, and selecting the authentication method for that resource. This creates a reusable project-level configuration rather than requiring each agent to store or duplicate search credentials independently.

For Foundry agents that use Azure AI Search, the Azure AI Search tool requires a project_connection_id, which is the resource ID of the project connection to Azure AI Search. This allows multiple agents to reference the same managed connection while using the configured endpoint and authentication settings consistently. RBAC may be part of a keyless authentication design, but it does not by itself create a centrally managed Foundry credential configuration. Disabling key-based access improves security posture but does not connect the agents. A managed private endpoint addresses network isolation, not credential centralization. Reference topics: Microsoft Foundry project connections, Azure AI Search tool, project connection IDs, authentication, and agent grounding.

First selection:

mcr.microsoft.com/azure-cognitive-services/textanalytics/sentiment

Second selection:

https://contoso.cognitiveservices.azure.com

Completed command:

docker run --rm -it -p 5000:5000 --memory 8g --cpus 1 \

mcr.microsoft.com/azure-cognitive-services/textanalytics/sentiment \

Eula=accept \

Billing=https://contoso.cognitiveservices.azure.com \

ApiKey=xxx

The image mcr.microsoft.com/azure-cognitive-services/textanalytics/sentiment is the official Microsoft Container Registry image for Azure AI Language sentiment analysis. The Billing argument must reference the endpoint of the provisioned Azure AI Language resource associated with the supplied API key. It is not the address used by applications to invoke the locally running container.

Azure AI containers require three licensing and metering parameters: Eula=accept, a valid Billing endpoint, and ApiKey. Without all three values, the container does not start. The command maps host port 5000 to container port 5000, allocates 8 GB of memory and one CPU, creates an interactive terminal, and automatically removes the stopped container. Applications subsequently invoke the locally hosted service through an address such as http:// < vm-address > :5000. The Azure endpoint remains responsible for metering and authentication; analyzed customer text is processed by the container rather than sent to the billing endpoint.

Study Guide alignment: Implement text analysis solutions — perform sentiment analysis and opinion mining, deploy Azure Language containers, and configure container billing parameters.

Prompt shields action: Set action to block.

Additional mitigation: Enable Spotlighting.

The correct configuration is to set the Prompt Shields document attack action to block and enable Spotlighting . Prompt Shields in Microsoft Foundry are designed to detect attempts to manipulate model behavior through adversarial input. Microsoft distinguishes document attacks from direct user prompt attacks: document attacks are malicious instructions embedded in third-party content such as documents, webpages, emails, or other externally supplied material. In this scenario, the embedded text inside uploaded screenshots is third-party content and can attempt to override the agent’s instructions. Setting the action to block prevents detected document-attack content from being processed normally, which is required because the goal is prevention rather than passive logging or annotation.

Spotlighting is the additional mitigation because it marks or transforms document content so the model treats it as lower trust than system and user instructions. Microsoft’s Foundry guidance describes Spotlighting as a Prompt Shields subfeature that helps protect against indirect or embedded document attacks by tagging input documents with special formatting to indicate lower trust. A custom blocklist is insufficient for unknown attacks, and OCR alone only extracts the malicious text; it does not mitigate prompt injection. Reference topics: Prompt Shields, document attacks, guardrails, Spotlighting, multimodal safety, and prompt injection defense.