Pass the Microsoft Azure AI Engineer Associate AI-103 Questions and answers with CertsForce

The correct configuration is an API key security scheme . For Microsoft Foundry Agent Service OpenAPI tools, the OpenAPI specification must declare authentication through the components.securitySchemes section and use a scheme of type apiKey when the external service expects a key in a header. Microsoft’s OpenAPI tool guidance states that API key authentication requires updating the OpenAPI spec security schemes with one scheme of type apiKey, and the tool then uses the associated project connection to supply the key value at runtime. This allows the key stored in Project1’s connection to be injected automatically when the tool is invoked.

A header parameter defined separately for each operation is not the correct approach because credentials should not be modeled as ordinary operation parameters. The Foundry guidance explicitly indicates that parameters requiring the API key should be removed from the OpenAPI spec because the API key is stored and passed through a connection. A Bearer token security scheme is used for bearer-token-style authorization, not a generic weather API key passed in a custom HTTP header. Azure Key Vault is a secret store, but the scenario already stores the key in a Foundry project connection. Reference topics: Microsoft Foundry Agent Service, OpenAPI tools, project connections, API key authentication, and OpenAPI security schemes.

The solution does not meet the goal. Increasing temperature changes the sampling behavior of the generative model, not the completeness-checking logic of the application. Microsoft’s Azure OpenAI reference defines temperature as a sampling control where higher values make output more random, while lower values make output more focused and deterministic. Raising the value can increase variation and creativity, but it does not ensure that all required regulatory clauses from the retrieved policy documents are included.

The reported issue is a recall/completeness failure: relevant clauses are already present in retrieved content, but the generated summary omits them. Microsoft Foundry RAG evaluator guidance defines Response Completeness as whether a response covers critical information compared to expected information or ground truth, and distinguishes it from groundedness, which checks that responses do not go beyond grounding context.

A more suitable implementation would add a reflection, verification, or completeness review pass that compares the draft summary against the retrieved clauses and revises the response before returning it. Increasing temperature could make outputs less predictable and may worsen omission risk. Reference topics: model parameters, temperature, RAG response completeness, retrieved context, and model reflection.

The LangChain service will appear in Traces without configuring a tracer: No

Setting different OTEL_SERVICE_NAME values separates the services in Application Insights: Yes

When using enable_content_recording=False, prompts and tool data will be captured in the telemetry: No

The first statement is No because a separate LangChain or LangGraph application must emit telemetry through the configured tracing integration. Microsoft’s LangChain tracing guidance states that you configure AzureAIOpenTelemetryTracer, attach it to the runnable or agent through callbacks, and then inspect the emitted traces in Azure Monitor. The troubleshooting guidance also states that missing LangChain or LangGraph spans are caused by tracing callbacks not being attached to the run.

The second statement is Yes . In OpenTelemetry, OTEL_SERVICE_NAME maps to the service.name resource attribute. Azure Monitor Application Insights uses cloud role names to represent separate services, and Microsoft states that when multiple services emit to the same Application Insights resource, cloud role names must be set so services are represented properly.

The third statement is No . enable_content_recording=False is specifically used to redact message content and tool call arguments from traces. Microsoft also advises disabling content recording in production and not storing secrets, credentials, or tokens in prompts or tool arguments. Reference topics: Microsoft Foundry tracing, LangChain tracing, OpenTelemetry service naming, Application Insights, and secure telemetry configuration.

credential = DefaultAzureCredential

response = openai_client.responses.create

The correct authentication class is DefaultAzureCredential because the requirement is Microsoft Entra-based authentication, and this credential supports managed identity in hosted Azure environments. The Microsoft Foundry quickstart for Python shows the project client being created with AIProjectClient(endpoint=PROJECT_ENDPOINT, credential=DefaultAzureCredential()), which enables the Foundry SDK to authenticate without using API keys or embedded secrets. The same guidance shows creating an OpenAI-compatible client from the project by calling project.get_openai_client().

The correct Responses API method is create because the application must send a new prompt to the deployed model and receive generated output. Microsoft’s Foundry quickstart demonstrates the exact pattern: response = openai.responses.create(model= " gpt-5-mini " , input= " ... " ), followed by reading response.output_text. The retrieve operation is used to fetch an existing response, not submit a new inference request, and compact is not the correct method for generating a model response. AzureKeyCredential would violate the Microsoft Entra managed identity requirement, while ClientSecretCredential uses an application secret rather than managed identity. Reference topics: Microsoft Foundry SDK, AIProjectClient, Microsoft Entra authentication, DefaultAzureCredential, and Azure OpenAI Responses API.

The solution does not fully meet the goal. Image moderation is appropriate for one part of the risk: blocking unsafe image content before the image is processed. Azure AI Content Safety provides image APIs that detect harmful content, and its harm categories and severity levels can be used to classify and block objectionable image content. This addresses unsafe photos, but it does not address hidden instructions embedded in images.

The second risk is prompt manipulation through extracted image text. After OCR extracts text from the uploaded image, that text becomes untrusted third-party content supplied to a generative model. Microsoft defines document attacks as malicious instructions embedded in third-party content, where the objective is to cause the model to execute unintended commands or alter intended behavior. Prompt Shields are the control designed to detect user prompt attacks and document attacks, including indirect attacks that come from uploaded or referenced content.

Therefore, image moderation alone is incomplete. A complete mitigation would combine image moderation for harmful visual content with Prompt Shields for document attacks, and optionally Spotlighting, so extracted or embedded text is treated as lower trust. Reference topics: Azure AI Content Safety, image moderation, Prompt Shields, document attacks, indirect prompt injection, and multimodal safety.

The correct answer is B. Use real-time speech to text to process streaming audio input . The scenario requires live transcription from a continuous telephony stream, with transcript text appearing within a few seconds while the call is still in progress. Azure Speech in Foundry Tools real-time speech recognition is specifically intended for immediate transcription scenarios such as call center assistance, dictation, and live meeting captioning. Microsoft’s Speech guidance describes real-time speech to text as processing audio input and returning transcriptions in real time, which matches the supervisor monitoring requirement.

Batch transcription is inappropriate because it processes stored audio files after recording, not an active live stream. Speech translation is used when the primary goal is translating speech into another language, not simply producing live same-language call transcripts. Text to speech performs the reverse operation by generating spoken audio from text and does not transcribe inbound calls. Real-time speech to text provides the low-latency streaming recognition path required for live operational monitoring. Reference topics: Azure Speech in Foundry Tools, real-time speech recognition, streaming audio input, call center transcription, and live captions.

Metrics to enable: Model Availability Rate and Provisioned Utilization

Diagnostic log to collect: trace

The correct metrics are Model Availability Rate and Provisioned Utilization . Model Availability Rate identifies whether failures are caused by service-side model unavailability because it is calculated from total calls minus server errors. Provisioned Utilization identifies resource-limit conditions because Microsoft states that when utilization reaches or exceeds 100%, calls are throttled and HTTP 429 errors are returned. This directly maps to the reported peak-hour rate-limit errors.

The correct diagnostic log is trace . For an internal Q & A scenario, trace logging is required to analyze question-answering behavior, including unanswered questions. Microsoft’s custom question answering analytics guidance states that diagnostic logging stores telemetry and chat logs and instructs enabling Trace in addition to Audit, RequestResponse, and AllMetrics. The sample Kusto queries for unanswered questions inspect the answer, question, score, and knowledge base ID, and filter unanswered results by a score of zero.

RequestResponse is useful for request status and latency, and Audit is for administrative operations, but neither is the best diagnostic category for analyzing Q & A inference behavior such as “No relevant information found.” Reference topics: Foundry monitoring, model availability, provisioned utilization, diagnostic logging, custom question answering analytics, and trace logs.

Yes, the solution meets the goal. The problem is not retrieval availability, because the required regulatory clauses are already present in the retrieved policy documents. The failure occurs during generation: the agent produces a summary that omits required content. A reflection pass is the correct application-level control because it adds a verification step before the response is returned. The pass can compare the draft answer against the retrieved clauses, detect missing mandatory content, and trigger regeneration or revision until the summary includes the required clauses.

This aligns with Microsoft Foundry’s evaluation and observability model, where generated responses are assessed for reliability, groundedness, relevance, and quality throughout the AI application lifecycle. Foundry observability guidance describes evaluation as a mechanism for measuring response quality and improving AI outputs across development and production workflows. The Azure AI evaluation SDK also defines completeness as the extent to which a generated response contains all necessary and relevant information with respect to the provided ground truth. Reflection operationalizes that quality check inside the application flow, rather than merely reporting the defect after the fact. Reference topics: model reflection, response completeness, RAG generation quality, retrieved context verification, and agent response optimization.

The correct indexing approach is to use an indexer to extract image data into a normalized_images collection . In Azure AI Search enrichment pipelines, embedded images in PDFs are not passed directly from the text content field into OCR. Instead, the indexer must perform document cracking and image extraction by enabling the indexer image action. Microsoft’s Azure AI Search documentation states that image-processing skills such as OCR and image analysis expect normalized images, and that enabling imageAction causes embedded images to be extracted and normalized for downstream skills.

The OCR skill is designed to receive image input from /document/normalized_images/*. Microsoft’s skillset tutorial specifically states that the OCR skill assumes a normalized_images field exists and that this field is generated by setting the indexer imageAction configuration to generateNormalizedImages. The document extraction skill reference also confirms that generateNormalizedImages creates an array of normalized images during document cracking for OCR and image analysis.

Option A is incorrect because OCR does not run directly against the index content field. Option B maps outputs after enrichment; it does not extract images. Option D reshapes data but does not create the required normalized image collection. Reference topics: Azure AI Search indexers, AI enrichment, OCR skill, imageAction, and normalized_images.

The solution does not meet the goal. Prompt Shields for user prompts are designed to detect direct attempts by a user to manipulate the model through the prompt itself. In this scenario, the malicious instructions are embedded inside uploaded images and then introduced into the model context through extracted image text. That pattern is an indirect prompt injection or document attack, not merely a direct user-prompt attack. Microsoft’s Prompt Shields guidance distinguishes between user prompt attacks and document attacks, and states that document attacks involve harmful instructions embedded in supplied documents or third-party content.

The solution is also incomplete because users can upload unsafe images. Azure AI Content Safety includes image APIs that detect harmful content in images and support moderation across modalities. A complete mitigation would combine image moderation for unsafe visual content with Prompt Shields for document attacks, and optionally Spotlighting, so OCR-derived or embedded image text is treated as lower-trust context. Prompt Shields for user prompts alone would not reliably block unsafe images or hidden instructions extracted from those images. Reference topics: Azure AI Content Safety, Prompt Shields, user prompt attacks, document attacks, image moderation, and multimodal safety.