The Human Is an Async API — Melanie Warrick, Temporal

A blocking ask-the-human call breaks in production. Durable workflows with a wait condition and signal let an agent pause for minutes or weeks and resume after a worker crash without losing state.

• Temporal's Melanie Warrick argues durability belongs in the agent harness, using Temporal's workers, workflows and activities to track state, shown with Google ADK and LangGraph agents.
• Two Temporal primitives, a wait condition and a signal, let an agent pause for a human and resume when the answer arrives, in both human-to-agent and agent-to-human flows.
• In the live demo she kills the worker mid-approval, then brings it back and the workflow recovers and replays with no lost work.
• On whether a human should be in the loop at all, she weighs the cost of the agent being wrong against alert fatigue.

• human-in-the-loop — Requiring a person's approval at specific points in an automated process, chosen so the irreversible steps are the ones a human sees.
• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
• agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.

• videoAgents That Write Their Own Tools at Runtime — Sandhya Subramani, AWS
• videoAI Coding Agents Are Breaking Big Codebases — Dan Adler, Sourcegraph
• videoKeyword Search Is Dying. Is Your Catalog Ready for AI Agents? — PayPal
• videoDashboards Are Dead — Sarah Simionescu, Composio

• videoEvery step you take, every call you make: the reliable agent stack — Giselle van Dongen, RestateAI Engineer
• videoEvolution of agentic surfaces — Gagan Bhat & Isabella Kai He, AnthropicAI Engineer
• videoNo Memory, No Harness: Why the Database Is the Last Line of Defense — Kay Malcolm, OracleAI Engineer

Checking sign-in…

Loading comments…