Important Microsoft AI-103 Exam Questions

Answer: B

Explanation:

The solution does not meet the goal. A completeness evaluation flow is useful for detecting incomplete responses, but detection and blocking do not improve the response itself. Microsoft Foundry RAG evaluators define Response Completeness as a metric that measures whether a response covers all critical information from the expected response or ground truth. It is a system evaluation signal used to assess response quality and produce pass/fail or scored results.

In this scenario, the issue is that the agent omits required regulatory clauses even though the clauses are present in retrieved content. Blocking low-scoring responses would prevent incomplete answers from being returned, but it would not revise the summary, add the missing clauses, or improve the generation process. The appropriate improvement is to add a response-generation control such as a reflection or verification pass that checks the draft summary against the retrieved policy content and regenerates or amends the answer before returning it. Evaluation can support the quality gate, but by itself it is an assessment mechanism, not a completeness-enhancement mechanism. Reference topics: Microsoft Foundry RAG evaluators, response completeness, grounded generation, reflection, and response quality optimization.

Answer: D

Explanation:

The correct answer is D. Use real-time speech to text for incoming audio and text to speech for agent responses. The workflow requires continuous audio input, low-latency transcription for reasoning, and spoken output back to the user. Azure Speech in Foundry Tools real-time speech to text is designed for immediate transcription from streaming audio, which satisfies the incoming-audio side of the interaction. Text to speech provides the outbound spoken response path after the agent generates its answer.

This pattern aligns with Microsoft's real-time voice-agent architecture. The Voice Live API overview explains that low-latency speech-to-speech systems integrate speech recognition, generative reasoning, and text-to-speech functionality to create natural voice experiences. It also identifies contact centers as a key scenario and highlights low perceived latency for end users. Embeddings do not decode audio into conversational speech. Batch transcription introduces file-oriented delay and is not suitable for turn-taking. Speech translation is only appropriate when translating between languages and does not provide the required reasoning-plus-spoken-response loop. Reference topics: Azure Speech in Foundry Tools, real-time speech to text, text to speech, voice agents, low-latency interaction, and conversational turn-taking.

Answer: B

Explanation:

The correct observability signal is B. groundedness evaluation metrics. In a RAG solution, the key diagnostic question is whether the generated answer is supported by the retrieved context. Microsoft Foundry's built-in evaluator reference defines Groundedness as the metric that measures how grounded the response is in the retrieved context, with scoring that indicates whether the model's claims are supported by the provided source material.

This matches the issue after a content update. If retrieved chunks are stale, misleading, incomplete, or poorly aligned with the user query, groundedness results can show that generated responses are not reliably supported by the retrieved documentation. The RAG evaluator guidance explains that groundedness focuses on whether the response avoids content outside the grounding context, while other process metrics such as retrieval evaluate how relevant the retrieved chunks are. Latency traces are useful for performance troubleshooting, not response accuracy. Indexer status can reveal ingestion failures, but it does not show whether retrieved content is influencing generated answers negatively. Prediction drift is a model monitoring concept and is not the primary signal for RAG grounding quality. Reference topics: Microsoft Foundry observability, RAG evaluators, groundedness, retrieved context, and response quality evaluation.

Answer: D

Explanation:

The correct answer is D. prompt shields for documents. The OCR text is extracted from uploaded images and appended as additional context, so it is third-party content rather than a direct trusted user instruction. Microsoft Foundry Prompt Shields distinguish between user prompt attacks, which are malicious instructions directly supplied as user prompts, and document attacks, which are hidden or embedded instructions in third-party content such as documents, emails, webpages, or grounded data. Microsoft also notes that Prompt Shields analyze indirect attacks embedded in input documents or images.

This scenario is an indirect prompt injection pattern: an uploaded screenshot may contain text that says to ignore the system prompt or perform unauthorized actions. Because the OCR output is being passed to the multimodal model as contextual content, the appropriate protection is Prompt Shields for documents, which scans externally sourced context for malicious embedded instructions before generation. Protected material text detects known copyrighted text in model outputs, not prompt injection. Image moderation detects harmful visual content categories, not malicious instructions in extracted context. Prompt Shields for user prompts are less precise here because the risk comes from document-like content derived from the uploaded image. Reference topics: Prompt Shields, document attacks, indirect prompt injection, multimodal safety, OCR-derived context, and Foundry guardrails.

Answer: A

Explanation:

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.