#fleets

Show HN: Airlock – Policy-as-code for fleets of AI coding agents

My name is Matt and I am building Airlock. Airlock is going to be an open standard on managing autonomous fleets of engineering agents. I am seeking constructive feedback on the direction of this project and also asking what are your major pain points with managing AI use at larger businesses. Right now I am running my own company using this framework with a total of 23 workflows across four large scale projects. Airlock is still really early, only 3-4 weeks old. Airlock's configuration standard is aimed to be open source and I will also open source the backplane once I gain a bit more confide

Show HN · EN

How to Run Better Research With Agent Fleets

In the current safety landscape, researchers are encouraged to use as many agents as possible, even in “fleets,” where a large number of them go out and run experiments while you, uh... wait for them to come back? I've spent the last few months of the Anthropic Fellows Program trying this out. My first attempts were naive, but after a few iterations I found an approach that works well for me. Research is a double loop I want to propose a mental model of research as a double loop, an idea that builds on double-loop learning (Argyris, 1977). The outer loop is reserved for the inputs we currently

LessWrong · EN

From IoT Fleets to Agent Fleets: Why I Wrote C.H.A.R.T.E.R.

C.H.A.R.T.E.R. is a fail-closed standard for governing a fleet of AI agents: one small file per agent lists every model, tool, host, and limit it may use, and the loader that runs it is the only door.

CodeNSolder · EN