AI-103 Developing AI Apps and Agents on Azure

What's inside

AI-103 doesn't test whether you can call a model. It tests whether you can build, secure and ship AI apps and agents on Azure, and pick the right service every time.

This independent study guide for the Microsoft Certified: Azure AI Apps and Agents Developer Associate exam distils what AI-103 really expects you to understand into the comparisons, design choices and traps that AI developer decisions turn on. AI-103 replaced AI-102 in 2026, and the book is written for the new exam's focus on Microsoft Foundry, agents and generative AI.

Organised by technology

Thirteen chapters, each readable on its own and together covering all five AI-103 skills areas:

• Foundry foundations: resources, projects and deployments, deployment types and upgrade policies, keyless identity and private networking, quotas, monitoring, evaluation and CI/CD.
• Responsible and generative AI: guardrails, Azure AI Content Safety and Prompt Shields, prompt engineering, parameters, structured output, model router and fine-tuning.
• Agents: Foundry Agent Service, tools including file search, Azure AI Search, web search, OpenAPI and MCP, memory, workflows and human oversight.
• Vision, language and speech: image and video generation, multimodal understanding, Azure Vision, text analysis, translation, speech and Voice Live agents.
• Knowledge and extraction: Azure AI Search indexing, vector and hybrid search and retrieval-augmented generation, Content Understanding and Document Intelligence.

Inside

• Comparison tables for every close call, such as which service, which tool, which deployment type or which analyzer fits a requirement.
• 80+ Common trap callouts that name the answers that look right but aren't, and explain what's right instead.
• 10 diagrams, from Foundry resources and projects and guardrail intervention points to agent tools, voice agents, the indexer pipeline and hybrid queries.
• Key takeaways at the end of every chapter for fast revision.
• A glossary of nearly 500 terms, each linked to Microsoft Learn, with a free online version for print readers.

Up to date

Azure AI changes quickly. This edition reflects Microsoft's documentation as of October 2026, including recent retirements such as the Assistants API, DALL-E 3 and Speech intent recognition, and notes where older material and today's product differ.

Understanding, not memorising

This book contains no exam questions. It explains the knowledge the exam expects, so you can answer questions you have never seen and apply the same judgement to real AI solutions.

Written by Tony Rough, a cloud architect with more than twenty years in IT infrastructure who holds the Azure Solutions Architect Expert, Azure Administrator and Azure Security Engineer certifications.

Part of the Ultra Transcenders series from Distilled Press. An independent publication, not affiliated with, sponsored by or endorsed by Microsoft Corporation.

Chapters

1. Microsoft Foundry: models, resources and deployments
2. Securing AI solutions: identity, keys and networking
3. Operating AI solutions: quotas, monitoring, evaluation and CI/CD
4. Responsible AI, guardrails and Azure AI Content Safety
5. Building generative applications: prompts, parameters and quality
6. Building agents with Foundry Agent Service
7. Image and video generation and multimodal understanding
8. Azure Vision: image analysis and OCR
9. Text analysis with Azure Language and language models
10. Translation: text, documents and speech
11. Speech and voice agents
12. Azure AI Search and retrieval-augmented generation
13. Document and content extraction

Plus an appendix glossary of 400+ terms, each linked to Microsoft Learn, and free online for print readers.

Sample diagrams

Free study notes

Some sections of the book, free to read online:

• Guardrails in Microsoft Foundry: intervention points, Prompt Shields and actions

  Where guardrails check an agent run, what Prompt Shields catch, and when to block or annotate.

• Choosing agent tools in Foundry Agent Service

  File search, Azure AI Search, Bing grounding, function, OpenAPI, MCP and code interpreter tools compared.

• Agent oversight: approvals, constraints and tool-access controls

  How to keep humans in the loop and limit what an agent's tools can do.

• Prompt engineering techniques for Azure AI apps

  System messages, few-shot examples, chain of thought and grounding, and which fix suits which prompt problem.

• Azure AI Search indexers, skillsets and the knowledge store

  The indexer pipeline stages, built-in and custom skills, and knowledge store projections.

• Vector, hybrid and semantic search in Azure AI Search

  Vector fields and profiles, HNSW vs exhaustive KNN, hybrid queries with RRF, and the semantic ranker.

• Azure Content Understanding: analyzers, modes and structured output

  Prebuilt and custom analyzers, field extraction methods and Markdown output for RAG.

• Video generation with Sora 2 in Microsoft Foundry

  What Sora 2 can generate, its parameters and limits, and how the asynchronous jobs work.