Ensuring your code works when AI testing isn’t enough | BRK208

Technical talk about building AI systems that scale for humans and machines, ensuring reliable code, and scalable systems.

Seating for this session is first-come, first-served. Add it to your schedule to plan your day and arrive early to secure a spot.

To learn more, please check out these resources:
* https://aka.ms/build26-next-steps
𝗦𝗽𝗲𝗮𝗸𝗲𝗿𝘀:
* Simon Willison
𝗦𝗲𝘀𝘀𝗶𝗼𝗻 𝗜𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻:
This is one of many sessions from the Microsoft Build 2026 event. View even more sessions on-demand and learn about Microsoft Build at https://build.microsoft.com

BRK208 | English (US) | Developer tools & frameworks
Breakout | (300) Advanced
#MSBuild

Chapters:
0:00 - Emergence of term 'Agentic Engineering' for professional AI-assisted coding
00:03:36 - Measuring productivity with AI-generated code and quality concerns
00:11:44 - Introducing Active Refactoring for Better Engagement
00:19:19 - Refining Documentation Style: Avoid Opinions and Promotional Tone
00:22:12 - Introduction to sandboxed iframes and their secure isolation capabilities
00:27:00 - Agentic engineering and parallels with accessibility improvements
00:27:50 - Revisiting 'The Mythical Man-Month' and its relevance to modern agentic development
00:34:49 - Choosing Go over Rust for readability and testing model understanding of complex compilers
00:35:59 - Using AI to develop in unknown languages and build native apps through agentic coding

Видео Ensuring your code works when AI testing isn’t enough | BRK208 канала Microsoft Developer