Production agents need more than model calls and memory. Long-running systemsA long-running AI agent maintains task state and continues observing, deciding, and acting across an extended period. also need durable progressDurable workflow execution preserves progress so a multi-step process can resume after interruptions using recorded completion state., retry and recovery behaviorAI agent recovery restores a workflow to a safe, known state after an agent error, interruption, or failed run., isolated state for concurrent sessions, communication between agents and tools, and controls that can cancel or redirect work already in progress.
The demonstration uses a Slack-connected research workflow to show how an event journalAn agent audit trail is an ordered, durable record of an AI agent's instructions, decisions, tool calls, state changes, identities, and outcomes. can restore progress after tool failures instead of restarting the entire run. Durable steps can also suspend without consuming compute while waiting for human approval, then resume from the recorded point when a response arrives.
Persistent sessions are modeled as stateful virtual objectsA stateful agent preserves task information across multiple events and model calls so its AI behavior can continue coherently over time. with isolated histories and serialized execution. Signals can inject new context or cancel a running call chain, while shared gateways can add policy checks and concurrency limits around model access. Underneath, an event-driven distributed log persists journal events, state, timers, and inter-service requests.
Watch on YouTube
