the async framing maps cleanly if you think about it in terms of control flow rather than latency. the real distinction isn't "runs for a long time", it's whether the orchestrator yields control and gets notified via callback/event vs. polling a status endpoint.

most things people call "async agents" today are really just synchronous RPC calls with a long timeout. the agent blocks the caller's context window the entire time. true async means the calling agent can spawn the task, context-switch to something else, and resume when it gets a structured completion signal - basically await semantics but for agent-to-agent or agent-to-human handoffs.

the hard engineering problem isn't the async dispatch, it's state serialization: how do you snapshot enough context that the agent can resume coherently after an arbitrary pause without re-reading the entire conversation history?

that's where most implementations i've seen fall apart.