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

AI-103 Practice Question 15: Toolbox Shared Tools

Microsoft Azure AI Apps and Agents Developer Associate (AI-103) · Test 2 · question 5 of 10

Implement generative AI and agentic solutionsmedium

A platform team supports fourteen agents: some are Foundry prompt agents, the rest are code agents built on Agent Framework and LangGraph. All fourteen wire up the same six internal tools, each with its own copy of the connection settings and credentials. When one backing API changed its auth scheme last quarter, the team had to edit and redeploy every agent. They want the tools defined once, credentials handled centrally, and a tool change rolled out without touching agent code.

What should they build?

Select one answer
Show answer and explanation

Answer:

  • B. A toolbox: define the six tools once and expose them to every agent through a single managed MCP-compatible endpoint

A toolbox is the Foundry construct for exactly this problem. You curate a set of tools once and expose them behind one MCP-compatible endpoint, with centralized credential injection, token refresh and policy enforcement using Microsoft Entra ID and OAuth identity passthrough. Toolboxes are *Foundry-homed but not Foundry-bound*, so the LangGraph and Agent Framework agents consume the same endpoint as the prompt agents. Versioning closes the loop: create a new toolbox version, test it, promote it to default, and every consuming agent picks it up with no redeployment.

- A is wrong because an OpenAPI tool still has to be attached and configured, with its own authentication, on each of the fourteen agents. It consolidates the *API surface*, not the per-agent configuration and credentials that caused the churn. - C is wrong because it multiplies the problem: six new function apps to operate, and each agent still holds its own tool wiring. It also changes the hosting model for no stated reason. - D is wrong because a shared package only helps agents written in a language that can import it, and every agent still has to be rebuilt and redeployed to pick up a new version, the exact cost they are trying to remove.

Reference: What is Toolbox in Microsoft Foundry?

Practice Test 2 ›

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.