Gulp: Real-Time Self-Improvement for AI Agents
Summary
Osmosis is a framework that helps your AI agents learn in real-time (similar to DeepSeek R1s post-training loop) in order to make them better, faster, and more responsive.On the first run, we scored 21.5% accuracy, which is 60% better than base 4o performance (16X more expensive!). ).If youre building AI agents and want to make them better, faster, and more responsive, wed love to chat! Email kasey@gulp.ai or book time here.AI agents still struggle with novel and complex (multi-step) tasks. This ends up negatively affecting performance while also driving up inefficient inference costs for users.Osmosis builds and maintains a library of an agents previous interactions. From there, he worked at various VC firms focusing on AI and data investments before deciding to jump back into building.Andy (CTO) previously worked at TikTok, where he joined as an early member of the data infrastructure team and eventually became a tech lead, running data infrastructure for recommendations across the core TikTok app, Shop, Live, and more.