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

  1. Microsoft Foundry documentation — start here, understand the hub/project model
  2. Get started with Azure AI services — Microsoft Learn path
  3. Develop generative AI with Azure OpenAI — Microsoft Learn path
  4. Azure AI Agent Service overview — agents, tools, threads
  5. Official AI-103 study guide — Microsoft Learn