Exam AI-103 · 250 practice questions

AI-103 study guide: Developing AI Apps and Agents on Azure

Exam AI-103, Developing AI Apps and Agents on Azure, leads to the Microsoft Certified: Azure AI Apps and Agents Developer Associate certification, an intermediate-level credential for AI engineers and developers. According to Microsoft's study guide, a candidate is an Azure AI engineer who builds, manages and deploys agents and AI solutions that take advantage of Microsoft Foundry.

The guide says you should have experience developing apps by using Python, and be familiar with the capabilities of general AI, generative AI and Azure services. The role works with business stakeholders, solution architects, data scientists, DevOps engineers and cloud security engineers to design, implement and maintain AI solutions.

These study pages follow the skills measured as of April 16, 2026. Each skill area below links to a hub that restates what the study guide expects, then lists every practice question for that area grouped by skill group. Each question page shows the scenario, all answer options with the correct answer highlighted, the explanation, a deep dive into the topic and the Microsoft Learn pages it is based on.

Skills at a glance

Plan and manage an Azure AI solution Exam weight 25–30% Choosing Foundry services and models, setting up and deploying solutions, operating them securely, and applying responsible AI. Skill groups: Choose the appropriate Foundry services for generative AI and agents; Set up AI solutions in Foundry; Manage, monitor, and secure AI systems; Implement responsible AI across generative AI and agentic systems. 69 practice questions · 16 of 16 skills covered Implement generative AI and agentic solutions Exam weight 30–35% Building generative apps and agents with Foundry, then tuning, observing and orchestrating them in production. Skill groups: Build generative applications by using Foundry; Build agents by using Foundry; Optimize and operationalize generative AI systems. 83 practice questions · 16 of 16 skills covered Implement computer vision solutions Exam weight 10–15% Generating and editing images and video, multimodal understanding with Content Understanding, and responsible AI for visual content. Skill groups: Design and implement image- and video-generation solutions; Design and implement multimodal understanding workflows; Implement responsible AI for multimodal content. 33 practice questions · 16 of 16 skills covered Implement text analysis solutions Exam weight 10–15% Language model text analysis (entities, summaries, sentiment, translation) and speech for agentic interactions. Skill groups: Apply language model text analysis; Implement speech solutions. 32 practice questions · 8 of 8 skills covered Implement information extraction solutions Exam weight 10–15% Retrieval and grounding pipelines with search and enrichment, and extracting structured content from documents. Skill groups: Build retrieval and grounding pipelines; Extract content from documents. 33 practice questions · 8 of 8 skills covered

What the study guide says about the exam

A score of 700 or greater is required to pass.
Most questions cover features that are generally available (GA). The exam may contain questions on Preview features if those features are commonly used.
The bullets under each skill illustrate how the skill is assessed; related topics may also be covered.
Exams are updated periodically. The English version is updated first, and localized versions follow approximately eight weeks later.

Sources: Study guide for Exam AI-103, Microsoft Certified: Azure AI Apps and Agents Developer Associate and Exam scoring and score reports on Microsoft Learn. TheAzureAI is an independent project and isn't affiliated with Microsoft.

Prefer to test yourself first? Take the practice quiz and come back to the study pages for anything you miss. Start a quiz →