After a year of putting AI agents with Yempik into production, here is the boring truth I keep running into: when an agent is unreliable, the model is almost never the reason. The 

Co-founder of Yempik. AI agents and automations in production, not in slides. Building cowork-os in public.

One year of shipping agents in production, and the boring truth about what actually breaks.

The reliability problem in AI agents is almost never the model

github

Read the articles written by Raffaele Zarrelli on Peerlist