AI-103 Practice Question 94: Computer Use Tool Guardrails

Microsoft Azure AI Apps and Agents Developer Associate (AI-103) · Test 10 · question 4 of 10

Implement generative AI and agentic solutionshard

An operations team wants an agent to submit maintenance tickets in a decades-old internal web portal. The portal exposes no API of any kind, only a browser-rendered UI, so no OpenAPI, function-calling, or MCP tool has anything to call. The team wants the agent to work the portal the way a person would: look at the screen and simulate clicks and keystrokes.

Which tool fits, and what precaution is essential before it runs unattended?

Show answer and explanation

Answer:

C. The computer use tool, run only against a low-privilege virtual machine or sandboxed environment with no access to sensitive data, requiring end-user approval of any pending safety check before the action executes

The computer use tool exists for interfaces with no API: it lets an agent "interpret screenshots and automate UI interactions like clicking, typing, and scrolling" through a screenshot-action-screenshot loop. Microsoft's guidance is explicit that it should run only "on low-privilege virtual machines that do not contain sensitive data or credentials," and that the API raises pending_safety_checks for things like prompt injection or sensitive-domain access; the calling application must "pause automation, require an end user to review the request, and only continue after you send acknowledged_safety_checks."

- A is wrong because the code interpreter's managed sandbox is built for running and analyzing code and files, not for vision-driven UI control, and it isn't where Microsoft's UI-automation guardrails apply. - B is wrong on two fronts: a function tool needs something to call, and this portal has no API (a scripted UI walkthrough isn't what the tool invokes), and embedding a standing, high-privilege service credential in a hosted function directly contradicts the no-sensitive-access guidance for automated UI control. - D is wrong because the OpenAPI tool consumes a real OpenAPI specification for an existing API; hand-writing a specification over rendered HTML pages describes no such API and isn't a supported or reliable substitute.

Reference: Use the computer use tool for 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.