DoorDash engineers build long-running AI agents

DoorDash is rolling out long-running AI agents to handle work that doesn't fit into quick, single-shot queries. Instead of spinning up a model, running a task, and shutting down, the agents stay alive — monitoring, responding, and chaining together decisions over longer timeframes.

The shift matters because delivery work is inherently continuous. Orders don't arrive in neat batches; they come in waves, with updates, reroutes, and customer messages that pile up while the previous ones are still being processed. Long-running agents can track multiple threads at once instead of starting fresh every time.

Why this matters for us: as more of us work delivery and gig apps, we're seeing the backend shift from quick snapshots to always-on systems — and that affects how our orders are routed, how fast we get updates, and how much of our time is being managed by machines that never sleep.