Free sections from Ultra Transcenders AI-103: Developing AI Apps and Agents on Azure, on the comparisons and decisions the exam keeps asking about.
Where guardrails check an agent run, what Prompt Shields catch, and when to block or annotate.
File search, Azure AI Search, Bing grounding, function, OpenAPI, MCP and code interpreter tools compared.
How to keep humans in the loop and limit what an agent's tools can do.
System messages, few-shot examples, chain of thought and grounding, and which fix suits which prompt problem.
The indexer pipeline stages, built-in and custom skills, and knowledge store projections.
Vector fields and profiles, HNSW vs exhaustive KNN, hybrid queries with RRF, and the semantic ranker.
Prebuilt and custom analyzers, field extraction methods and Markdown output for RAG.
What Sora 2 can generate, its parameters and limits, and how the asynchronous jobs work.