Brains vs Hands: How to Run AI Agents Safely in Production — Viren Baraiya
AI Engineer — Oct 8, 2026 — talk
Why watch
Viren Baraiya explains how to run AI agents safely in production by separating the LLM (the brain that plans) from a deterministic, durable harness (the hands that execute). This talk is for platform engineers and DevOps building production AI agent systems who need reliable, long-running agents with approval gates, idempotent steps, and recorded side effects. He demonstrates an SRE agent whose plan gets compiled into a Conductor workflow with re-planning loops.