Agents spend most of their lives waiting: provisioning a cluster takes fifteen minutes, a human replies next week, and an alert might not fire for a month. Most runtimes hold a process open through all of it, so a machine stays up for weeks to do a few minutes of real work.
A reactive agent is a running process only while it has something to do. The rest of the time it could be a row in a database or a file on disk, until something outside sends it an event.
I'll cover what reactive agents look like in implementation, and how MCP is evolving to enable them.
