JITA Learning · Microsoft · Field Guide
AI-103 · Developing AI Apps and Agents on Azure
Build working judgment for Azure AI application and agent development.
What you should expect
Build working judgment for Azure AI application and agent development.
This Field Guide develops a working mental model of Azure AI application and agent development. You will connect choose the appropriate Foundry services, models, retrieval, grounding, memory, tools, and multimodal capabilities, design RAG and agent patterns that match workload, data, and interaction requirements, reason about prompt, model, retrieval, tool, and orchestration failure boundaries, and apply responsible AI, content-safety, identity, and access controls. You are not just memorizing feature names; you are learning what owns the requirement, what can fail, and how to verify the outcome.
What you will learn
- choose the appropriate Foundry services, models, retrieval, grounding, memory, tools, and multimodal capabilities
- design RAG and agent patterns that match workload, data, and interaction requirements
- reason about prompt, model, retrieval, tool, and orchestration failure boundaries
- apply responsible AI, content-safety, identity, and access controls
- recognize why one technically plausible alternative loses under the stated requirement
- apply Changed Fact reasoning and verify the design or implementation through operational evidence
Decision skills you will practice
- identify the governing requirement
- compare the nearest plausible alternative
- apply Changed Fact reasoning
- trace prerequisites, dependencies, and failure paths
- verify configured state, effective state, runtime outcome, and negative-path evidence
Who this is for
developers and AI engineers building production applications and agents with Microsoft Foundry and Azure AI services
Use this when you need to learn the architecture, mechanics, dependencies, tradeoffs, failure paths, and verification logic behind the certification.
Decisions you will learn to distinguish
- model problem vs retrieval or grounding problem
- RAG workflow vs agent/tool orchestration
- successful generation vs evaluated and operationally safe response
Why JITA is different
Microsoft explains the platform. JITA teaches the decision.
Microsoft Learn explains the services, features, and documented behavior that support Azure AI application and agent development. JITA connects those capabilities into decisions: what owns the requirement, what the nearest alternative is, what changes when one fact changes, and what evidence proves the implementation worked.
How to choose:
Use the Field Guide to build understanding. Use the Exam Preparation Guide to test whether that understanding survives exam-style decisions.