learn

Azure AI Certification Path 2026 — AI-901 and AI-103

Current Azure AI certification path for 2026, covering AI-901 fundamentals and AI-103 for developing AI apps and agents on Azure.

Last verified metadata is optional and can be added to each content file when a guide has been reviewed against an authoritative source.

Azure AI Certification Path 2026 — AI-901 and AI-103

Microsoft's Azure AI certification landscape changed in 2026. The retired AI-900 and AI-102 exams should now be treated as legacy study material. For a current path, use AI-901 for fundamentals and AI-103 for AI application and agent development.

Beginner: AI-901

Microsoft Azure AI Fundamentals (AI-901) is the current fundamentals exam. It covers foundational AI concepts, machine learning on Azure, computer vision, natural language processing, and generative AI workloads.

Use it when you want a broad introduction before moving into hands-on AI development.

Practitioner: AI-103

AI-103: Developing AI Apps and Agents on Azure is aimed at Azure AI engineers building and operating AI solutions and agents with Microsoft Foundry.

Key areas include:

  • Planning and managing Azure AI solutions
  • Generative AI and agentic solutions
  • RAG, retrieval, grounding, and vector search
  • Model and application evaluation
  • Computer vision and multimodal workflows
  • Text analysis and information extraction
  • Security, monitoring, quotas, scaling, and cost
  • Responsible AI, guardrails, safety, and governance

AI fundamentals → Python → LLMsRAG → agents → evaluation → security → observability → production architecture → AI-103 scenarios

Important migration note

If you have older AI-900 or AI-102 notes, keep them for conceptual background, but verify service names, APIs, objectives, and exam guidance against the current Microsoft Learn material before using them for exam preparation.

Connected knowledge

AI Engineer Roadmap 2026RAGAI agentsAI evaluationAI security

Official sources

Learning checkpoint

Mark this guide complete to include it in your local Engineering Journey.

Engineering companion

Learn → troubleshoot → design → prepare → test

Explore the knowledge graph

Knowledge path

Connected concepts

Explore the knowledge graph