Sign in to confirm you’re not a bot
This helps protect our community. Learn more

How Microsoft Engineers Build AI - Learn About Scalable RAG-enabled AI Apps

Microsoft Developer
589K subscribers
<__slot-el>
<__slot-el>
2.2K views 2 months ago
We are thrilled to introduce the first episode of new Microsoft Engineering Video Series: How Microsoft Engineers Build AI! In this series, we will be deep diving with Microsoft engineers on how they are building AI applications here at Microsoft. We’ll cover many different topics in this series, starting with one of the most common updates that developers are making with AI: implementing retrieval-augmented generation (RAG) into applications. In this video we will learn directly from the Microsoft Engineering team on how they used RAG to develop the Ask Learn function on Copilot for Azure at scale! From discussing chunking strategies to how to avoid hallucination, deep dive into how Microsoft builds their own AI.! ✔️Get Started: AI for Developer Hub: https://aka.ms/AIforDeveloper 📌 Let's connect: Brian Steggeman | LinkedIn   / briansteggeman   Eric Imasogie | LinkedIn   / eric-imasogie   Tianqi Zhang | LinkedIn   / tianqi-zhang-07342831   F …...more
...more

Introduction

0:00

Demo

0:49

What is RAG?

3:25

What part of this product is being used from Microsoft?

7:30

Why do you think it was necessary to create this plugin for Ask Learn?

9:50

What was so special about this project?

11:35

What challenges did you face building this tool?

13:01

If there is a bad response, how do you improve it for next time?

17:10

Were there any surprises you faced and how did you deal with them?

18:24

What steps do you take to clean and preprocess data before it’s ingested into the system?

21:25

There is a lot of information on Microsoft Learn, how did you break it down, what was your strategy?

24:08

How did you manage data changes consistently?

27:25

How do you keep a balance between a fast and good answer?

29:49

How do you know that Ask Learn is doing well and how do you monitor it?

32:33

How do you avoid hallucination and ensure safety?

34:34

Security Concerns

36:22

What advice would you give to developers who are new to building RAG-based applications?

37:28

What are some mistakes/traps to avoid?

39:33

Conclusion

43:20
How Microsoft Engineers Build AI - Learn About Scalable RAG-enabled AI Apps
47Likes
2,246Views
Feb 262025
We are thrilled to introduce the first episode of new Microsoft Engineering Video Series: How Microsoft Engineers Build AI! In this series, we will be deep diving with Microsoft engineers on how they are building AI applications here at Microsoft. We’ll cover many different topics in this series, starting with one of the most common updates that developers are making with AI: implementing retrieval-augmented generation (RAG) into applications. In this video we will learn directly from the Microsoft Engineering team on how they used RAG to develop the Ask Learn function on Copilot for Azure at scale! From discussing chunking strategies to how to avoid hallucination, deep dive into how Microsoft builds their own AI.! ✔️Get Started: AI for Developer Hub: https://aka.ms/AIforDeveloper 📌 Let's connect: Brian Steggeman | LinkedIn   / briansteggeman   Eric Imasogie | LinkedIn   / eric-imasogie   Tianqi Zhang | LinkedIn   / tianqi-zhang-07342831   Frank Boucher | LinkedIn   / fboucheros   📖 Blog post: https://devblogs.microsoft.com/engine... 00:00 Introduction 00:49 Demo 03:25 What is RAG? 07:30 What part of this product is being used from Microsoft? 09:50 Why do you think it was necessary to create this plugin for Ask Learn? 11:35 What was so special about this project? 13:01 What challenges did you face building this tool? 17:10 If there is a bad response, how do you improve it for next time? 18:24 Were there any surprises you faced and how did you deal with them? 21:25 What steps do you take to clean and preprocess data before it’s ingested into the system? 24:08 There is a lot of information on Microsoft Learn, how did you break it down, what was your strategy? 27:25 How did you manage data changes consistently? 29:49 How do you keep a balance between a fast and good answer? 32:33 How do you know that Ask Learn is doing well and how do you monitor it? 34:34 How do you avoid hallucination and ensure safety? 36:22 Security Concerns 37:28 What advice would you give to developers who are new to building RAG-based applications? 39:33 What are some mistakes/traps to avoid? 43:20 Conclusion

Follow along using the transcript.

Microsoft Developer

589K subscribers