agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
Why it matters
If you're building computer-use or GUI-operating agents, this lays out a perceive-plan-act architecture plus an open-source annotation/verification agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → aimed at the core reliability problem — agents recovering from unexpected UI states rather than blindly clicking.
Key quotes
“click clicking was actually the easy part. What we didn't solve is the actual work”
Antje Barth
“if your agent one in four times deletes a database, you will never touch that agent again”
Antje Barth
“It's because code is verifiable. You can run it, you can test it, you can check it and you can be for sure that it worked.”
Antje Barth
“Knowledge work is messy and heck the whole real world is really messy.”
Antje Barth
“You don't necessarily need a bigger brain. What you need is this shared context.”
videoWhy AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMax
videoYour company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQL
videoTethered: Our Agents Are Us — Shu Fang, Two Sigma
videoAgents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Town
