8 episodes. Conversations with the people building AI in production
OpenHands CEO Robert Brennan on running fleets of AI coding agents: persistent cloud environments, credential isolation, and evaluation that decides when work needs a human.
Episode notesCisco is becoming AI-native by redesigning both how its 90,000 employees work and how autonomous agents are secured.
Episode notesLoop engineering turns repetitive AI work into systems that act, evaluate, remember, improve and escalate — without constant human prompting.
Episode notesAn agent becomes useful when the model is surrounded by a harness: tools, files, memory, triggers, permissions and monitoring. A tour of Dmitry Shapiro's always-on system.
Episode notesProduction voice AI depends on far more than a strong model: turn detection, interruption handling, memory, guardrails, escalation — and the latency-versus-reasoning trade-off.
Episode notesShubham Saboo runs a scheduled agent squad — chief of staff, research, triage, content — that supports a 110,000-star GitHub repo and escalates only what needs a human.
Episode notesSuperhuman CPO Noam Lovinsky explains how AI-native organizations collapse roles, turn PMs into builders, redesign hiring and connect model behavior to UX.
Episode notesShopify VP Product Mani Fazeli explains why products must serve both humans and AI agents—from machine-readable catalogs and SimGym to agentic checkout.
Episode notes