End-to-End Model Development on Microsoft Foundry

Описание: In this session, we explore the end-to-end journey of designing and developing AI solutions with Microsoft Foundry models. The session is structured around four key phases of the model development journey.

We begin with Model Understanding, where you discover the Foundry model catalog and build intuition around core model capabilities. Next is Model Selection, focusing on how to choose the right model for a given use case using benchmarks, evaluations, and leaderboards. We then move into Model Customization, covering how models can be adapted through techniques such as context engineering, fine‑tuning, and compression to better meet application needs. Finally, we close with Model Observability, highlighting how evaluations, tracing, and monitoring help ensure models behave safely, reliably, and effectively at scale.

🔗 The Java Script AI Build-a-thon: https://aka.ms/JSAIBuildathon

📌 This session is a part of a series, learn more here: https://aka.ms/JS-Buildathon

Chapters:
0:09 Welcome & Session Housekeeping
1:04 Welcome to Day 3 of the JavaScript AI Buildathon
2:34 What Is the JavaScript AI Buildathon?
3:22 Buildathon Structure & Schedule Overview
4:26 Where to Find Quests, Resources & Discord
5:50 Today’s Topic: End-to-End AI with Microsoft Foundry
7:02 Introduction to Microsoft Foundry Platform
8:26 Model Development Journey Overview
10:12 From Prompting to Customization
12:29 Modern AI Development & Agents Explained
14:30 Getting Started: CodeSpaces & Project Setup
18:44 Creating an Azure Foundry Project
20:10 Choosing the Right Model in Foundry
23:37 Model Benchmarking & Tradeoffs
25:43 Deploying and Testing Your First Model
28:44 Connecting Code to Foundry
31:08 Prompt Engineering & Grounding with Data
34:30 Why and When to Fine-Tune Models
36:33 Fine-Tuning & Model Distillation Explained
38:32 Monitoring Fine-Tuning Jobs
42:43 Deploying Fine-Tuned Models
43:48 Building Agents with the Foundry SDK
45:15 Observability, Tracing & Evaluations
49:05 Quality & Safety Evaluations
51:01 Red Teaming & Adversarial Testing
55:02 Recap: From Prototype to Production AI
57:12 AMA & What’s Next
1:01:28 Closing & Upcoming Sessions

#MicrosoftReactor #learnconnectbuild

[eventID:26773]