Now

Right now I am deep in agentic work, as always. Efficient inference and data flywheels are the bread and butter of it. Most of my thinking centers on the agentic platform at Omilia and the memory framework beneath it, the part that lets agents remember, hold context, and act reliably across long-running work.

This month the foreground is a keynote at AWS Trailblazers in Madrid, 16–17 September. I will talk about Omilia: how we made AI work profitable, and the reorg and AI transformation we have been pushing forward over the last couple of years.

I shipped From Prompt to Loop, a free field guide to agentic loops: small systems that run an AI agent for you, on a schedule, while you sleep, that ship on green with no human in the seat. I run a fleet of these loops the way I once ran a crew on a warship. Scoped stations. Clear orders. A hand only on what you cannot take back.

Part I of my new book, The Rookie Manager, is out and free. All nine chapters of it, on the career switch nobody is talking about: you were great at the work, someone handed you a team, and nobody trained you for any of it. The full book goes live late September.

I also recorded an AWS podcast episode with Miguel Alava on what it takes to run conversational AI at enterprise scale, owning your models rather than renting them, and why the infrastructure underneath outlasts any single model. It went live on 4 August.

I write about all of it as The Warship CTO, and I post daily on LinkedIn and Substack. Crews, not committees. Loops, not turns.

The tool was never the skill. The thinking behind it was.