AI-103 Developing AI Apps and Agents on Azure Questions and Answers

The correct model type is a large language model (LLM) . The scenario requires an agent that can reason over retrieved documentation, synthesize context-aware answers, and generate detailed natural language responses. Microsoft Foundry RAG guidance defines Retrieval Augmented Generation as a pattern that combines search with large language models so responses are grounded in organizational data, which directly matches the use of Azure AI Search for internal product documentation.

An LLM is also the correct fit for deep, multi-step reasoning across long contexts. Azure AI Search agentic retrieval guidance states that complex chat and agent scenarios use an LLM to break a user query into smaller focused subqueries for better coverage over indexed content. Microsoft also describes Azure AI Search as a way to ground agents and chatbots in proprietary enterprise data for accurate, context-aware responses.

A multimodal model is unnecessary because the requirements are text-focused, not image, audio, or video based. A key phrase extraction model performs narrow text analytics and cannot generate detailed answers. An SLM may reduce cost and latency, but the stated need for deep reasoning and long-context synthesis favors an LLM. Reference topics: Microsoft Foundry RAG, Azure AI Search grounding, agentic retrieval, and model selection for generative AI agents.

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 correct choice is to use a model cascade that routes the requests to different models . In Microsoft Foundry, this pattern aligns with model routing: simple, low-risk prompts can be handled by smaller, faster, lower-cost models, while complex prompts can be escalated to more capable or reasoning models. Microsoft’s Foundry model router guidance states that the router optimizes cost and latency while maintaining comparable quality by using smaller, cheaper models when they are sufficient and larger or reasoning models when the task requires more advanced capability.

This directly matches the scenario: most traffic consists of simple FAQs, so routing those requests to efficient models reduces average latency and token-processing cost. Advanced reasoning requests still receive high-quality responses because they are routed to models with stronger reasoning capability. Microsoft’s model router documentation also explains that routing decisions consider prompt difficulty, cost, quality, latency, and conversation context, making it suitable for diverse chat workloads.

Increasing max_tokens for all requests would usually increase cost and latency. Sending all requests to a smaller model risks poor quality for complex questions, while sending all requests to the most capable model wastes cost and latency on simple FAQs. Reference topics: Microsoft Foundry model routing, model selection, generative AI optimization, latency management, and cost-aware AI application design.

The correct answer is D. Set the output_content_format=ContentFormat.MARKDOWN value . Azure Document Intelligence Layout API can return extracted document content in Markdown format, preserving semantic structure such as headings, paragraphs, sections, tables, and other layout elements. Microsoft’s Document Intelligence layout guidance shows the Python SDK pattern for analyzing a document with the prebuilt-layout model and setting output_content_format=ContentFormat.MARKDOWN in the begin_analyze_document call. The Markdown output is returned in the top-level content section of the analysis result.

This minimizes development effort because the service produces structure-preserving Markdown directly, rather than requiring custom post-processing to reconstruct sections and table formatting from raw OCR spans. Microsoft’s Markdown output documentation states that specifying Markdown output produces semantically structured content that maintains paragraphs, headings, tables, and other document elements in their proper hierarchy.

Option A only changes validation behavior and does not generate Markdown. Option B requests figures, not structured Markdown. Option C uses an incorrect parameter name; the documented SDK setting is output_content_format, not content. Reference topics: Azure Document Intelligence Layout API, Markdown output, PDF analysis, table extraction, and Foundry Tools document processing.

The correct answer is Azure Content Understanding in Foundry Tools . The scenario requires more than basic OCR because scanned invoices have varied layouts and multipage tables. Content Understanding is designed for intelligent document processing and provides OCR, layout detection, table extraction, field extraction, confidence scores, and grounding in a managed service. Microsoft describes Content Understanding as a service that transforms unstructured content into structured outputs and supports invoice processing by extracting and validating fields from complex documents.

This also meets the requirement to avoid training a custom model. Content Understanding includes prebuilt and domain-specific analyzers, including invoice and procurement-style document processing, and Microsoft states that these analyzers provide structured extraction without custom training. It generalizes across visual template variations by using semantic document categories rather than requiring separate models per invoice layout.

Azure Machine Learning would increase administrative effort because it requires model development, training, deployment, and monitoring. Azure Language is optimized for text analytics tasks such as classification and entity extraction after text is available, but it does not provide document layout analysis or multipage table structure extraction. Reference topics: Content Understanding, intelligent document processing, OCR, layout analysis, analyzers, field schemas, and structured extraction.

scope = " {{userId}} "

tools = [memory_tool]

The correct scope value is {{userId}} because the requirement is per-authenticated-user memory isolation without the client application manually generating user identifiers. In Microsoft Foundry Agent Service memory, the scope parameter partitions memory items inside the memory store. The official guidance states that when the memory search tool is attached to an agent, setting scope to the user identity template enables per-user memory isolation; the service resolves the end-user identity from the request header when provided, or falls back to the Microsoft Entra tenant ID and object ID of the caller. This matches the requirement to isolate stored preferences by authenticated user automatically.

The tools property must be [memory_tool] because the MemorySearchTool instance is created earlier and must be attached to the PromptAgentDefinition. Foundry guidance shows the memory search tool being passed in the agent definition as tools=[tool] , allowing the agent to read from and write to the configured memory store during conversations.

" session " and {{conversationId}} would limit continuity to a session or conversation instead of enabling long-term recall across separate conversations. [mem_store_name] is a list containing the store name, not a tool definition. Reference topics: Foundry Agent Service memory, memory stores, memory search tools, scope, and per-user isolation.

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 correct built-in skills are Azure OpenAI Embedding and Text Split. The case study requires an indexing pipeline that enables semantic and vector search over the product sheets stored in Azure Blob Storage, so Agent1 can retrieve relevant product information for natural language customer questions. For a RAG pipeline, long PDF content must first be broken into retrievable chunks, and each chunk must then be vectorized for semantic similarity retrieval.

Microsoft’s Azure AI Search integrated vectorization guidance states that you create a skillset that calls the Text Split skill for chunking and the Azure OpenAI Embedding skill to vectorize the chunks. The Text Split skill breaks text into chunks and provides positional metadata, making it suitable when downstream embedding skills have input-length limits. The Azure OpenAI Embedding skill connects to an embedding model deployed in Azure OpenAI or a Microsoft Foundry project and generates embeddings during indexing.

Language Detection, Entity Recognition, and key phrase extraction can enrich text, but they do not create vector embeddings. Merge is useful for combining OCR text with document text, but it does not satisfy the core vector-search requirement. Reference topics: Azure AI Search skillsets, Text Split skill, Azure OpenAI Embedding skill, integrated vectorization, and RAG indexing.

The correct recommendation is Azure AI Search. The case study states that the product detail sheets are stored as PDFs in storage1, and that Agent1 must be enabled to retrieve and use detailed product information from those sheets. It also specifies that the indexing pipeline must enable semantic and vector search, and that Agent1 must answer natural language questions about product details by using the product sheet information. Azure AI Search is the Azure service designed to ingest content from sources such as Azure Blob Storage, create searchable indexes, and support keyword, semantic, hybrid, and vector retrieval for Retrieval Augmented Generation (RAG) solutions.

Microsoft’s Azure AI Search guidance states that integrated vectorization can chunk content and generate embeddings during indexing, enabling vector search over source documents. It also states that Azure AI Search supports text and vector queries and can improve raw content for search-related scenarios through enrichment pipelines. Azure Translator is unrelated to retrieval. Document Intelligence can extract document structure, but it is not the retrieval index for Agent1. Grounding with Bing Search retrieves public web content, not Contoso’s private PDFs in storage1. Reference topics: Azure AI Search, RAG, semantic search, vector search, Azure Blob Storage indexing, and agent grounding.

The correct answer is B. Modify the system message instructions . The case study states that Agent1 answers general questions about Contoso products and that the business requirement is for Agent1 to answer questions only about the products sold by Contoso . This is a behavioral boundary for the agent, so it should be implemented in the highest-priority instructions that define the agent’s role, allowed scope, and refusal behavior.

Microsoft Foundry guidance states that a system message is used to steer model behavior, define the assistant’s role and boundaries, and add safety or quality constraints for the scenario. The system message should instruct Agent1 to answer only when the question concerns Contoso products, use the configured Contoso product documentation as grounding, and politely refuse or redirect questions about non-Contoso products.

Top-p sampling and temperature control randomness, not business-domain scope. Increasing temperature would make responses less deterministic. Few-shot examples can support desired behavior, but examples alone are weaker than explicit system-level instructions for defining operating boundaries. Reference topics: system message design, prompt engineering, agent instructions, response constraints, and grounded generative AI behavior.

The correct recommendation is Azure Content Understanding in Foundry Tools . The case study states that Contoso’s finance department must manually review vendor invoices to verify that invoice details match vendor contract terms, and that the invoices contain tables, logos, and varied layouts that make consistent processing difficult. It also states that the planned solution must evaluate both the visual layout and textual content of the invoices.

Azure Content Understanding is designed for this type of multimodal document-processing workload. Microsoft describes Content Understanding as a Foundry Tool that processes unstructured and multimodal content, including documents and images, and transforms it into structured output for AI applications. It can use document analyzers to extract text, layout, tables, fields, and relationships from diverse document types.

Chat completions alone would not reliably extract structured invoice fields from complex layouts. Azure Document Intelligence can extract OCR, layout, and tables, but Content Understanding is the better end-to-end Foundry capability for combining visual and textual understanding with structured extraction for downstream verification. Image Analysis focuses on image-level visual features and is insufficient for invoice field and table review. Reference topics: Content Understanding, document analyzers, multimodal extraction, invoice processing, tables, layout, and structured JSON output.

The correct answer is B. Personally Identifiable Information (PII) Detection . The case study states that Agent1 must never reveal customer information , even if a document containing customer data is added accidentally to the product sheet repository in storage1. This is a privacy and compliance control requirement, so the appropriate capability is PII Detection.

Azure Language PII Detection is a Foundry Tools capability that identifies, classifies, and redacts sensitive information across text, conversations, and native documents. Microsoft states that PII Detection can be used to implement privacy controls, reduce sensitive data exposure, and support compliance requirements. In this scenario, PII Detection should be applied to retrieved product-sheet content and generated responses so customer names, contact details, identifiers, and other sensitive values are not exposed to users.

Prompt Shields are important for a separate requirement: protecting Agent1 from malicious instructions hidden in documents or embedded text. Microsoft describes Prompt Shields for documents as protection against hidden instructions embedded in external content. However, the option that directly satisfies the requirement to prevent disclosure of customer information is PII Detection. Self-harm and violence filters address harmful-content categories, not privacy leakage.

credential = DefaultAzureCredential()

agent = project_client.agents.get(agent_name=myAgent)

The correct authentication option is DefaultAzureCredential() because the case study states that API keys must not be used to access Foundry-deployed models and that Contoso developers must authenticate to Microsoft Foundry resources by using Microsoft Entra authentication. It also states that access to Project1 must be assigned to Agent1Dev Team by using the security group SC_Agent1_Dev . Microsoft Foundry authentication guidance recommends Microsoft Entra ID for production workloads because it supports least-privilege RBAC, per-principal auditing, and keyless authentication. AzureKeyCredential() would violate the no-API-key requirement, and None would not provide a valid credential.

The correct agent operation is get because the task is to access an existing agent named Agent1, not create a new version or retrieve a specific published version. Microsoft Foundry SDK examples show AIProjectClient created with DefaultAzureCredential() and then using project agent operations to create, retrieve, or interact with agents by name. To meet the compliance requirement, the group SC_Agent1_Dev must also be granted the appropriate project-scoped Foundry role, such as Foundry User, for Project1. Reference topics: Microsoft Entra authentication, Foundry RBAC, AIProjectClient, and project agent access.

Deployment type: Standard

Version update policy: Once the current version expires

The correct deployment type is Standard . The case study specifies that Project1 is deployed in an EU Azure region and that model-processed data must remain within the EU. It also requires scalable, high-throughput generative AI workloads that dynamically handle variable customer support traffic without reserved throughput capacity. In Microsoft Foundry Models, Standard is a pay-per-token deployment type that processes data in a single Azure region, while Global Standard can process requests across regions and Global Provisioned uses reserved provisioned throughput. Microsoft’s deployment-type guidance identifies Standard as single-region, pay-per-token, whereas Global Provisioned is cross-region with reserved capacity.

The correct version update policy is Once the current version expires . This keeps Agent1 on the selected model version during its supported lifecycle, which supports stable and consistent responses, but still preserves continuity by automatically moving to a supported replacement when the current version is retired. Microsoft’s model versioning guidance states that this policy updates only when the current model version expires, while upgrading when a new default is available changes the deployment sooner and opting out can cause the deployment to stop working after retirement. Reference topics: deployment types, regional data processing, model versioning, throughput capacity, and stable production deployments.

The correct answer is B. Modify the system message instructions . The case study states that Agent1 answers general questions about Contoso products and that a business requirement is for Agent1 to answer questions only about products sold by Contoso. This requirement defines the agent’s allowed domain and refusal boundary, so it must be expressed in the agent’s system-level instructions. Microsoft Foundry guidance states that system messages steer Azure OpenAI chat model behavior and are used to define the assistant’s role, boundaries, output format, and safety or quality constraints.

The system message should instruct Agent1 to answer only Contoso-product questions, use Contoso product documentation when available, and decline questions about non-Contoso products. This directly enforces the intended business scope at the highest instruction level. Few-shot examples can reinforce desired behavior but are not the primary control for defining mandatory operating boundaries. Top-p sampling and temperature are decoding controls; they influence randomness and diversity, not whether the agent restricts answers to a specific product domain. Increasing temperature would likely reduce consistency. Reference topics: Microsoft Foundry agent instructions, system message design, prompt engineering, response boundaries, and grounded generative AI behavior.