Uploaded November 2026 | Updated November 2026, 2 days ago
In a world of abundant models, winning means continuously adapting to customer contextโnot just choosing the best model. The hill-climbing machine connects inference, observability, evaluations, optimization, model selection, post-training, and RL into one learning loop. Every interaction improves quality, cost, and reliability, turning AI into a governed, self-improving business platform.
To learn more, please check out these resources:
* https://aka.ms/ignite26/next-steps/agent-platform
๐ฆ๐ฝ๐ฒ๐ฎ๐ธ๐ฒ๐ฟ๐:
* Steve Sweetman
* Naomi Moneypenny
๐ฆ๐ฒ๐๐๐ถ๐ผ๐ป ๐๐ป๐ณ๐ผ๐ฟ๐บ๐ฎ๐๐ถ๐ผ๐ป:
This is one of many sessions from the Microsoft Ignite 2026 event. View even more sessions on-demand and learn about Microsoft Ignite at ignite.microsoft.com
BRK242 | Agent Platform
Breakout | (200) Intermediate
#MSIgnite
In a world of abundant models, winning means continuously adapting to customer contextโnot just choosing the best model. The hill-climbing machine connects inference, observability, evaluations, optimization, model selection, post-training, and RL into one learning loop. Every interaction improves quality, cost, and reliability, turning AI into a governed, self-improving business platform.
To learn more, please check out these resources:
* https://aka.ms/ignite26/next-steps/agent-platform
๐ฆ๐ฝ๐ฒ๐ฎ๐ธ๐ฒ๐ฟ๐:
* Steve Sweetman
* Naomi Moneypenny
๐ฆ๐ฒ๐๐๐ถ๐ผ๐ป ๐๐ป๐ณ๐ผ๐ฟ๐บ๐ฎ๐๐ถ๐ผ๐ป:
This is one of many sessions from the Microsoft Ignite 2026 event. View even more sessions on-demand and learn about Microsoft Ignite at ignite.microsoft.com
BRK242 | Agent Platform
Breakout | (200) Intermediate
#MSIgnite










