✳flâneur — a map of the web's best reading

AddyOsmani.com - Long-running Agents

addyosmani.com · 4,154 words · saved by 1 readers

A long-running agent can keep making progress over hours, days, or weeks. It can do this across many context windows and sandboxes, recover from failure, lea...

A long-running AI agent can keep making progress over hours, days, or weeks. It can do this across many context windows and sandboxes, recover from failure, leave structured artifacts behind, and resume where it left off. For two years the dominant image of an “AI agent” has been a chat window with a clever loop in it. You type a goal, the agent calls some tools, you watch tokens stream by, you stop watching when the work runs out of patience or the context window fills up. That paradigm got us a long way, but it has a ceiling. The model forgets. It declares “task complete” when it isn’t. It r

Explore this link on the map →

saved by

related reading