Get Your CertAI-103PlayCompete
‹ All AI-103 questions

AI-103 Practice Question 81: Bing Grounding Connection Setup

Microsoft Azure AI Apps and Agents Developer Associate (AI-103) · Test 9 · question 1 of 10

Plan and manage an Azure AI solutionmedium

A team is building a prompt agent in Foundry Agent Service that must ground its answers in live public web results and return the bing_grounding tool's source citations for a compliance audit trail. The team has already provisioned and paid for a dedicated Grounding with Bing Search resource for this purpose. A developer holding only the Foundry User role on the project tries to add that resource as a project connection so the agent can reference it, but the Foundry portal blocks the action.

What should the team do to get the connection created and usable by the agent?

Select one answer
Show answer and explanation

Answer:

  • D. Have someone holding Foundry Project Manager on the project add the connection, then reference the resulting connection name or ID in the bing_grounding tool's configuration

Microsoft's prerequisites for Grounding with Bing Search split the work by role: Contributor on the resource group is needed only to provision the Bing resource and read its keys, while Foundry Project Manager on the Foundry project is the role required to create project connections. Foundry User is enough to build and run agents but doesn't include that permission, which is exactly why the developer's attempt was blocked. Once the connection exists, SDK samples resolve it by connection name (BING_PROJECT_CONNECTION_NAME) and REST samples use its full connection ID, either of which is passed into the bing_grounding tool's search configuration.

- A is wrong because General Web Search is a real, simpler alternative for basic live-web answers, but it doesn't use the resource the team already provisioned, and it doesn't produce the bing_grounding tool's citation output the compliance audit trail depends on. - B is wrong because Foundry Agent Consumer is the least-privilege role for *invoking* an agent's endpoint. It carries no data-plane or management permission to create project connections. - C is wrong because Contributor on the Bing resource is the role for provisioning that resource and retrieving its keys, a step the team already completed. It has nothing to do with the missing permission, which is on the Foundry *project*, not the Bing resource.

Reference: Use Grounding with Bing Search tools with the agents API

Practice Test 9 ›

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.