The thesis is that once an agent must remain responsive while doing long-running work, it stops being a chatbot and starts resembling an operating system. I’d show an architecture we’ve built at Miriel that separates real-time dialogue from deliberative work, with durable goals, a shared blackboard, system-call-like tool boundaries, and a scheduler that distinguishes progress, blocking, and runaway loops. It would be a practical technical talk, grounded in working software and actual failure modes, but aimed at giving application developers a different mental model for how serious agents should be built.
Andy Barkett is the Founder and CEO of Miriel, bringing over 20 years of engineering and technology leadership across AI, databases, robotics, and consumer tech. Previously, Andy worked on site reliability and search quality at Google and served as Director of Production Engineering at Facebook, where he led infrastructure, scalability, and performance for all major product lines. His executive background also includes serving as the first Chief Technology Officer for the Republican National Committee and leading technology strategy for Jeb Bush’s 2016 presidential campaign. In addition, he has served as CTO at Korbit, spearheading applied AI and big data implementations. Andy holds a B.A. in Political Economy from UC Berkeley and an MBA from UC Davis. He is an active angel investor, startup advisor, guest lecturer across computer science and business at UC Berkeley and UC Davis, and an advisor for UC Berkeley’s Political Economy program.
