Data engineer, then AI engineer in London. I build stuff with Claude and run agents on Kubernetes for a living.https://david.lequin.dev/en-gbhttps://david.lequin.dev/icons/icon-512.pnghttps://david.lequin.dev/https://david.lequin.dev/blog/hello-world/https://david.lequin.dev/blog/hello-world/Who I am, why I'm writing this blog, and what you can expect from it: honest notes on running AI agents in production.Tue, 13 Oct 2026 00:00:00 GMT<p>I'm David Lequin, a data person in London who spent the last decade-plus wrangling pipelines, warehouses and the occasional 3am page. Lately I've been wrangling AI agents instead, and discovering that they fail in familiar ways, only with more personality.</p> <h2>Why I'm writing</h2> <p>Getting an agent to do something impressive takes an afternoon. Getting it to do that same thing reliably, cheaply and observably, for real users, on a Tuesday, is a different job entirely. Most of what's written about agents covers the afternoon. I want to write about the Tuesday.</p> <h2>What to expect</h2> <ul> <li><strong>Agent infrastructure</strong>, including running agents on Kubernetes</li> <li><strong>Evals and observability</strong>: how you know the thing works, and notice when it stops</li> <li><strong>Data engineering for AI</strong>: the plumbing that decides whether any of it is useful</li> <li><strong>Production war stories</strong>: what worked, what didn't, and what caught fire</li> </ul> <p>I build most of this with Claude, so expect honest notes on that too, including the parts that didn't go to plan.</p> <h2>How this blog works</h2> <p>Everything is published here first, and cross-posted elsewhere with a canonical link back. If you'd rather not check in, there's <a href="https://david.lequin.dev/rss.xml">an RSS feed</a> and an email list, and the signup is just below.</p> <p>First real post soon. Something probably caught fire.</p> metaai-agentsdavid@lequin.dev (David Lequin)