AddyOsmani.com - Long-running Agents
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
saved by
related reading
- Killing Coding Agent Slop With Adversarial Self-Playusetelos.ai
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- Notes on the Software Factorybenedict.dev
- Building Effective AI Agents \ Anthropicanthropic.com
- Scaling long-running autonomous coding · Cursorcursor.com
- Towards self-driving codebases · Cursorcursor.com
- Scaling Managed Agents: Decoupling the brain from the hands \ Anthropicanthropic.com
- Harness design for long-running application developmentanthropic.com
- Arjun Virkarjunvirk.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Effective context engineering for AI agents \ Anthropicanthropic.com
- Prime Agent: A Self-Improving RLM Harnessarxiv.org