I gave a factory of AI agents 42 hours. It merged 17 pull requests
Over 42 hours (28 h 39 min of shifts across 12 runs), a line of AI agents cloned a competitor's features into my product and merged 17 pull requests to production. This is how the…
Over 42 hours (28 h 39 min of shifts across 12 runs), a line of AI agents cloned a competitor's features into my product and merged 17 pull requests to production. This is how the…
02My Samsung TV boots into Smart Hub: a wall of promoted shows, a Bixby banner, a "Samsung TV Plus" row I never asked for, and six tiles of apps I never open. Every press of the…
03Most of the marketing behind LLM Gateway was built with AI agents: the blog posts, the comparison pages, the model catalogue pages, the docs, the launch videos, the SEO audits. So…
04Seven weeks ago I published a post about DevPass that contained this sentence: Those three prices and that 3× multiplier have been constant since day one — every "pricing change"…
05In my last post about LLM Gateway I mentioned DevPass in passing as "the single biggest inflection" in the company's growth. This post is the zoomed-in version: how a flat-rate…
06In May 2025, Luca Steeb and I started building LLM Gateway, an open-source API gateway for Large Language Models. Twelve months later, it has processed over $470K in verified…
07“ In the late ’50s, a Cornell scientist named Frank Rosenblatt had proposed the world’s first neural network machine. It was called the Perceptron” Let’s start by defining the…
© Copyright 2016-2026, All Rights Reserved by Smakosh LLC