Sam Komesarook

Hard crashes are easy: the agent throws an error, you fix it, and you move on. The harder problem is drift, when the agent technically succeeds but slowly stops doing what you meant. Outputs become vaguer, tool choices grow stranger, and costs start to creep up.In this talk, the speaker examines how to detect behavioral drift before users notice, borrowing from process control theory and anomaly detection in industrial systems. The session explores what the benchmark of “normal” actually means, and how to build the feedback loops needed to catch drift early.

Agent demos are shiny; daily use is messy. In this talk I’ll share a handful of short, honest stories from shipping agent workflows with real teams—what we tried, how people reacted, what surprised us, and what we changed the next day. Rather than theory, you’ll hear concrete moments (wins, faceplants, near-misses) and the practical learnings that emerged. You’ll leave with clear and battle-tested principles that encompass the new world we are all approaching.