
Sign up to save your podcasts
Or


Scott Hanselman sits down with Allen Stewart, Partner Director of Software Engineering at Microsoft, to explore how AI agents with persistent memory are transforming scientific research and software engineering. Allen explains how his team built an AI system that learns from every investigation turning a 12-day autonomous drug discovery run into reusable knowledge that makes future research exponentially faster. Instead of starting from scratch each time, the AI inherits hypotheses, methodologies, and findings from previous work, saving hundreds of millions of tokens and weeks of effort.
By Scott Hanselman4.8
379379 ratings
Scott Hanselman sits down with Allen Stewart, Partner Director of Software Engineering at Microsoft, to explore how AI agents with persistent memory are transforming scientific research and software engineering. Allen explains how his team built an AI system that learns from every investigation turning a 12-day autonomous drug discovery run into reusable knowledge that makes future research exponentially faster. Instead of starting from scratch each time, the AI inherits hypotheses, methodologies, and findings from previous work, saving hundreds of millions of tokens and weeks of effort.

274 Listeners

38 Listeners

288 Listeners

887 Listeners

631 Listeners

83 Listeners

583 Listeners

287 Listeners

44 Listeners

990 Listeners

212 Listeners

190 Listeners

243 Listeners

62 Listeners

140 Listeners

68 Listeners

75 Listeners