AI-103 Practice Question 71: Pinning API Version

Microsoft Azure AI Apps and Agents Developer Associate (AI-103) · Test 8 · question 1 of 10

Plan and manage an Azure AI solutionmedium

A claims-processing service calls the Document Intelligence analyze REST endpoint from a .NET backend. Six months ago a developer wired the call to whatever api-version the sample code on the docs page showed at the time, which happened to be a dated preview release. Overnight, a batch of claims began failing because the JSON key the code reads for a bounding region had been renamed in the version now returned. Nothing in the application changed.

What should the team do to prevent this from recurring, and why?

Show answer and explanation

Answer:

A. Pin the api-version query parameter to a specific generally available release in code, and only move to a newer release after testing against it

Document Intelligence versions its REST API with a dated api-version parameter, and preview releases are explicitly temporary: Microsoft's own release history records that preview versions such as 2022-01-30-preview and 2021-09-30-preview were retired on a fixed date and that customers had to "update to the 2022-08-31 API version to avoid any service disruptions." Compatibility between preview versions, and between preview and GA, isn't guaranteed; response shapes can and do change, which is exactly the symptom here (a renamed JSON field). Pinning the call to a specific GA version keeps the response contract stable indefinitely; the team then upgrades deliberately, testing the new version's response shape before switching the pinned value in code.

- B is wrong because the API requires an explicit api-version on every request; there's no "unversioned, always-current" mode. Omitting or mishandling it doesn't opt out of versioning; it just risks calling an unintended version. - C is wrong because it treats the symptom, not the cause. A regex fallback is brittle and still has to be rewritten for every future field rename; it does nothing to stop the endpoint's shape from shifting under the application again. - D is wrong because it has the risk backwards: preview versions are the ones scheduled for retirement and the ones whose schema is still subject to change. Chasing the newest preview maximizes exposure to the exact failure the claims team just had, not minimizes it.

Reference: Azure Document Intelligence release history

Practice Test 8 ›

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.