AgentRun: a harness that learns repetitive jobs, codes its own solution, then gets out of the way
garrytan · x · 2026-09-19
Miguelrios announced AgentRun, a new agent harness built with @pidotdev and Jev from @typesafeai. Its goal: let an agent learn how to do a job, code itself a general solution, and then get out of the way.
The team focused deliberately on repeatable knowledge work — jobs their customers run thousands of times a day. Optimizing for that single use case and scale led them to a harness design that differs from typical agent frameworks.
More from coding & agent
- Grok agent hunting a parking spot found $986 of bogus charges and emailed for a refund — Baconbrix · 2026-09-19
- Xcode 27.1 hides an Action Bar for the iPhone Duo simulator — here's how to enable it — rudrank · 2026-09-19
- Jev and the Case for Deterministic Interfaces Over LLM Black Boxes — round · 2026-09-19
- Simulating a Small Village Where Every Agent Acts on Jev's Outputs — DevDminGod · 2026-09-19
- Dev proposes skill to wake an agent via cron polling once usage limits reset — StewartalsopIII · 2026-09-19
- AssemblyAI Hosts SF Tech Week Workshop Building Voice Agents Into Vintage Toys — AssemblyAI · 2026-09-19