‹ All AI-103 questions

AI-103 Practice Question 95: Client Side Function Calling Credentials

Microsoft Azure AI Apps and Agents Developer Associate (AI-103) · Test 10 · question 5 of 10

Implement generative AI and agentic solutionsmedium

A bank's customer-support web app lets a signed-in customer chat with an agent about their own accounts. To answer "what's my current balance," the agent needs an internal account API that authorizes requests using the customer's own delegated OAuth token, the token issued to the web app's session when that customer signed in, and never available anywhere else, including to the Foundry project or any identity it manages. The team wants live balance data without routing the call under a broad service identity that could see every customer's accounts.

Which tool should expose this capability to the agent?

Select one answer
Show answer and explanation

Answer:

  • A. A function-calling tool, where the web app itself executes the balance lookup using the token it already holds and returns the result to the agent

Function calling runs wherever the calling application runs: "Your app executes the function and returns the output." Here that application is the customer's own authenticated browser session, which already holds the delegated token the account API requires, nothing about that token needs to exist anywhere inside Foundry for the lookup to work, and the call is authorized exactly as the customer, not as any broader identity.

- B is wrong because the OpenAPI tool is a hosted tool: Foundry invokes the API directly using the *project's* managed identity, not the signed-in customer's; the account API would need to trust a single service principal for every customer, which is the broad access the bank wants to avoid. - C is wrong for the same reason: the Azure Functions tool authenticates as the function app's own identity, running inside Foundry's environment rather than the customer's session, so it never sees and cannot use the customer's delegated token. - D is wrong because an MCP server authenticates to the downstream API with its own service credential, again substituting a shared identity for the one credential that actually carries the customer's own authorization.

Reference: Use function calling with Microsoft Foundry agents

Practice Test 10 ›

Study guides for AI-103

AI engineer roadmap 2026: skills, certs and the orderAI engineer roadmap for 2026: skills to learn in order, AI engineer vs ML engineer, which certifications fit each stage, and what to skip.
AI-200 exam guide: Azure AI Cloud Developer AssociateAI-200 replaced AZ-204: what the Azure AI Cloud Developer exam tests, how it differs from AI-103, price in USD and INR, format and how to prepare.
How AI Is Changing Software Jobs: Where to PrepareHow AI is changing software jobs: what history shows, the evidence on junior developers, what Klarna learned, new AI roles and five domains to prepare for.
AI-901 exam guide: Azure AI Fundamentals after AI-900AI-901 replaced AI-900: learn what changed, how much Python and Microsoft Foundry you need, exam costs in India, and how to prepare.
Best AI certifications 2026: AWS, Google, Microsoft, ClaudeThe best AI certifications in 2026 from AWS, Google, Microsoft, Claude and Databricks, by level, with price, status and which one to take first.
Microsoft AI certification path 2026: which exam firstMicrosoft AI certification path for 2026 - AI-901, AB-730, AI-103, AI-200, AI-300, AB-100, AI-500 and GH-300 by role, and which exam to take first.
AI-103 Certification Guide: What Changed From AI-102The AI-103 certification replaced AI-102 in 2026. Exam format, cost, the five skill domains, what changed and how to prepare, with free practice questions.
What Is RAG? How Retrieval-Augmented Generation WorksWhat RAG is and how it works: chunking, embeddings, vector search, hybrid search, reranking, GraphRAG and agentic RAG on AWS, Google and Azure.
Prompt engineering vs RAG vs fine-tuningWhen to use prompt engineering, retrieval-augmented generation, fine-tuning or continued pre-training, compared on cost, freshness, hallucination and privacy.