Agents, page 2

Andon Labs Opened Its Danger Test to the Public. Its Own Stores Still Pay the Model More Than the Till.

16 minute read

· Agents

Andon Labs built Vending-Bench to measure the capability it considered most troubling: AI acquiring resources by running businesses. On 14 September it opened Pion, the platform that runs its own AI-operated store and cafΓ©, to anyone on a waitlist. Over the past 30 days both of those businesses spent more on model tokens than they took in sales, and the company’s simulated arena keeps recording cartels.

The Agents Lost $359.80. The Rest of the Number Is a Price List.

18 minute read

· Agents

Seven frontier models got $300 each and 72 hours to make money. They made none. The figure being quoted β€” nearly $3,200 lost β€” adds a real bank withdrawal to an imputed price on tokens that never moved through the accounts, and the same page reports two token totals that differ by a factor of fifty-one. The experiment is worth more than the number it produced.

Why Do AI Agents Forget? The Memory Stack, and the Three Ways It Breaks

13 minute read

· Agents

Agent memory is not one thing. It is four stores and a retrieval policy, and the binding constraint is almost never capacity β€” it is that long context degrades well below its stated limit, that nearly every published memory benchmark result is self-reported by the system’s own authors, and that a persistent store is a writable attack surface.

How I Built an Autonomous Desktop AI Companion Using AI Agents

6 minute read

· Agents

I wanted an AI that lived on my OS rather than in a browser tab β€” one that could see my screen and take over my mouse. Here is the three-layer architecture, and how I shipped it by directing a team of coding agents instead of writing it all myself.

Building for the Other 60%: Four Shifts Toward Industrial-Grade AI Agents

10 minute read

· Agents

Gartner expects over 40% of agentic AI projects to be canceled by the end of 2027. That is not a verdict on the technology β€” it is a description of a category maturing. Four shifts visible in the engineering and research literature describe what the surviving systems will look like.

The Autonomous Retention Engine: A Theory of Multi-Agent AI for SaaS Churn

14 minute read

· Agents

Churn is a structural interruption of promised future value, and the systems most companies use to watch for it are objects waiting to be polled. A theory of the retention engine: proactive agents over passive records, leading telemetry over lagging finance, cooperative architectures over silos β€” with a human at the boundary.

page 2 of 2 · 22 essays on Agents