Optimize generative AI model performance with Microsoft Foundry | AI-103 | Episode 5

Episode 5 of 26
For the full video series, visit: https://aka.ms/AI-103onYouTube

Explore techniques for improving generative AI application performance through prompt engineering, retrieval-augmented generation (RAG), and fine-tuning. Learn when to use each approach and how to evaluate improvements in response quality, tone, accuracy, and format.

Immerse in rich interactive materials with self-directed learning: https://aka.ms/AI-103onLearn

00:00 Video Start
00:05 Session Overview
14:27 Demo: Fine-tune a language model
25:02 Knowledge Check
25:49 Summary
27:01 Conclusion