Microsoft · AB-731
Prompts, grounding, and RAG
AB-731 · Lesson 2 of 8 · 8:27
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the AB-731 exam (Microsoft Certified: AI Transformation Leader). In this lesson: why prompt quality drives answer quality, the four elements of a good prompt (goal, context, sources, expectations), prompt templates and few-shot examples, grounding answers in trusted data, and how retrieval-augmented generation retrieves, augments, and generates, with Azure AI Search, without retraining the model. Includes three original practice questions.
Preview the topics
- A manager asks Copilot to write a project update, and gets something generic. Which change would most improve the next answer?
- A support chatbot must answer from the latest product manuals, which change every month, and cite them. Which approach fits best?
- In retrieval-augmented generation, what happens right after the relevant documents are retrieved?