AI-103 Study Guide: Azure AI Apps and Agents Developer Associate
New certification: AI-103 is the successor to AI-102. The beta exam opened in April 2026, with the exam going live in June 2026. It replaces the Azure AI Engineer Associate certification and adds a heavy focus on Microsoft Foundry and agentic AI development.
Overview
The AI-103 exam targets developers who build production-ready AI applications and agents using Microsoft Foundry and Azure AI services. Compared to AI-102, it shifts emphasis toward generative AI, prompt engineering, multi-agent orchestration, and the full Foundry platform — while still covering computer vision, NLP, and document intelligence as supporting skills.
Exam Details
| Detail | Information |
|---|---|
| Exam code | AI-103 |
| Certification | Azure AI App and Agent Developer Associate |
| Level | Associate |
| Passing score | 700 / 1000 |
| Duration | 100 minutes |
| Cost | $165 USD (varies by region) |
| Beta availability | April 2026 |
| Exam goes live | June 2026 |
| Predecessor | AI-102 (retires June 30, 2026) |
Skills Measured
Plan and Manage Azure AI Solutions (25–30%)
- Select appropriate Foundry services for generative AI and agent workloads
- Configure AI Foundry projects and hubs
- Manage access, security, and governance for AI resources
- Monitor and manage AI service costs and quotas
- Implement responsible AI practices and content filtering
Implement Generative AI and Agentic Solutions (30–35%)
- Build generative AI applications using the Azure AI Foundry SDK
- Apply prompt engineering techniques (few-shot, chain-of-thought, structured outputs)
- Implement Retrieval Augmented Generation (RAG) with Azure AI Search and embeddings
- Build AI agents using Foundry Agent Service
- Implement multi-agent orchestration patterns
- Integrate tools and function calling into agents
- Implement agent memory and context management
- Evaluate and optimize generative AI application quality
Implement Computer Vision Solutions (10–15%)
- Implement image and video generation using multimodal models
- Analyze images and video using Azure AI Vision and GPT-4o vision
- Implement multimodal understanding workflows
- Train custom vision models (image classification, object detection)
Implement Text Analysis Solutions (10–15%)
- Apply language models for text analysis (sentiment, entities, key phrases)
- Implement speech-to-text and text-to-speech with Azure AI Speech
- Build translation solutions with Azure AI Translator
- Implement custom language models (NER, CLU)
Implement Information Extraction Solutions (10–15%)
- Build retrieval and grounding pipelines using Azure AI Search
- Extract structured data from documents with Azure AI Document Intelligence
- Train custom document intelligence models
- Implement vector search and semantic ranking
Microsoft Foundry — What You Need to Know
Microsoft Foundry (formerly Azure AI Studio) is the central platform for building and deploying AI apps and agents. It is the dominant exam topic in AI-103. Key concepts:
AI-102 vs AI-103 — What Changed
| Topic area | AI-102 | AI-103 |
|---|---|---|
| Primary platform | Azure Cognitive / AI Services | Microsoft Foundry + Azure AI Services |
| Generative AI weight | ~10–15% | ~30–35% |
| Agentic AI | Not covered | Core domain — agents, tools, multi-agent |
| RAG | Introduced | Deep coverage including vector search |
| Computer vision | 15–20% | 10–15% (includes multimodal) |
| NLP / Speech | 30–35% | 10–15% |
| Document Intelligence | Part of knowledge mining domain | Information extraction domain |
| Evaluation | Not explicit | Covered — Foundry evaluators, quality metrics |
Recommended Study Path
- Microsoft Foundry documentation — start here, understand the hub/project model
- Get started with Azure AI services — Microsoft Learn path
- Develop generative AI with Azure OpenAI — Microsoft Learn path
- Azure AI Agent Service overview — agents, tools, threads
- Official AI-103 study guide — Microsoft Learn