technifyed

Microsoft via Microsoft Learn

Optimize generative AI model performance with Microsoft Foundry

Overview

Explore complementary strategies to optimize generative AI model performance, including prompt engineering, system messages, model parameters, Retrieval Augmented Generation (RAG), and fine-tuning. Learn when to use each strategy and how to combine them.

Syllabus 8

  1. Introduction 5 minutes
  2. Optimize model output with prompt engineering 10 minutes
  3. Ground your model with Retrieval Augmented Generation 10 minutes
  4. Fine-tune a model for consistent behavior 10 minutes
  5. Compare and combine optimization strategies 5 minutes
  6. Exercise - Optimize generative AI model performance 1.5 hours
  7. Module assessment 5 minutes
  8. Summary 5 minutes

Skills you'll practise

Microsoft Foundry

Advantages and disadvantages

Advantages

  • Free, official and kept up to date by Microsoft.
  • Free sandbox environments for many Azure exercises, no credit card needed.
  • Counts toward Microsoft certification exams (AZ-900, AI-900, PL-300…).
  • From Microsoft, a well-regarded name.
  • Free digital badge you can add to LinkedIn.
  • Completely free.
  • Self-paced: start any time.
  • A clear syllabus (8 parts) you can see before you start.

Disadvantages

  • Mostly reading, not video.
  • Focused on Microsoft products.

Some points apply to every course of this kind; see how we rank.

Free, with a free credential

  • Free: Sign in with any Microsoft account.
  • Badge: Finish it to earn a free badge on your Microsoft Learn profile.

Microsoft is in Tier 2: excellent universities and the companies that build the technology of our institution ranking (86/100).

Similar courses

Compare these

Stanford University · YouTube

Large Language Models (LLMs)

Explore the cutting-edge realm of Large Language Models (LLMs) with this expertly curated YouTube playlist. Featuring insights from industry leaders, educational content, and in-depth discussions, this selection highlights the latest advancements in LLM technology.

Free video26 videos, 42 hours

Stanford University · YouTube

Stanford CME295: Transformers and Large Language Models I Autumn 2025

This course explores the world of Transformers and Large Language Models (LLMs). You will learn the evolution of NLP methods, the core components of the Transformer architecture, along with how they relate to LLMs as well as techniques to enhance model performance for real-world applications. Throu…

Free video9 videos, 16 hours

Stanford University · YouTube

Transformers

Dive into the intriguing world of AI Transformers with this curated YouTube playlist. Featuring expert insights, educational content from leading organizations, and engaging discussions, this playlist keeps you informed about the latest breakthroughs in Transformer technology.

Free video16 videos, 17 hours

Stanford University · YouTube

Stanford CS25 - Transformers United

Stanford CS25: Transformers United Since their introduction in 2017, transformers have revolutionized Natural Language Processing (NLP). Now, transformers are finding applications all over Deep Learning, be it computer vision (CV), reinforcement learning (RL), Generative Adversarial Networks (GANs)…

Free video50 videos, 56 hours

Google · YouTube

AI at Google I/O 2024

Delve into cutting-edge topics like Generative AI and its applications, discover how Large Language Models (LLMs) are transforming the future of work, and find inspiration to integrate ML into your projects. Get ready to unlock new possibilities and build smarter, more powerful applications with th…

Free video40 videos, 22 hours

Harvard University · YouTube

CS50 Fall 2023 - Artificial Intelligence (live, unedited)

*** This is CS50, Harvard University's introduction to the intellectual enterprises of computer science and the art of programming. *** TABLE OF CONTENTS 00:00:00 - Welcome 00:14:13 - Introduction 00:16:25 - Image Generation 00:21:38 - ChatGPT 00:24:18 - Prompt Engineering 00:25:52 - CS50.ai 00:32:…

Free video1 hour

Enter your email and the official page opens. Phone is optional.