Building my master agent · in public

Most AI advice comes from people who never ran an operation.

I've been running operations for 20 years. Now I augment and automate real work
with my AI master agent. And I will teach you to build your own master agentA single AI system you direct, connected to your tools and data. It keeps context and calls its own skills and sub-agents to do real work.What is an AI master agent? →,
so that you can augment and automate your work yourself.
I'll even show you when AI is not the answer.
Because more often than not, it isn't.

Updates

What's new

Wins, upcoming talks, and what I'm building right now.

First place at Sprint Zero, the Techleap AI Hub hackathon
70 builders, around 20 teams, two rounds. ABN AMRO's challenge: tell whether the human on a banking video call is real. Instead of another deepfake detector, our team flipped it and built an app that proves a real person is present. It runs alongside any call with no plugins, reading LiDAR depth, rPPG and motion signals plus an ultrasonic fingerprint, scoring trust live and exchanging signed proofs over a secure channel. Demo and pitch built in two hours, judged to first place by a jury including Daniel Gebler (Picnic), Leonard Bukenya (Codam) and Lethabo Motsoaledi (Voyc). The prize: six months of full AI Hub membership for the team, worth €10,000, starting when the hub opens in September.
Co-presenting The Fractionals Live, Amsterdam
On stage with Dorothy Seguy, to a room of senior fractional operators (CMOs, CTOs, CPOs, founders), on human-led growth and AI-assisted execution. I'll show how AI agents and workflow design help you scale outreach and follow-up, prioritize the right conversations, and cut the manual work, without automating the human side away.
Building in public

I'm building a master agent from scratch

Not a chatbot, an operator. A personal master agent that plans, decides, and executes work across everything I do. It plans in Todoist, runs inside Conductor on Claude Code, and remembers across sessions, so its reasoning compounds instead of starting over. Each job goes to the right model: a frontier model to orchestrate, smaller ones to synthesize and search, local models for the cheap work. Label a task and it boots a session and runs it end to end.

I build it in the open, including the part most people hide: the first version failed, and I document exactly why. Every decision is recorded with its reasoning, so nothing gets re-litigated and the learning compounds. Along the way I release the parts as free skills, prompts, and patterns you can drop into your own setup. Next: a content engine that turns the work into posts, an observability layer to see what the agent does and spends, and the principles behind all of it.

Spinning out into products

The parts that prove themselves become products you can plug straight into your own stack. First up:

Agent observability dashboard: token usage, cost and cache-hit rates across Claude Code, Codex and local models

Agent observability dashboard

See exactly what your agents are doing, spending, and caching, in real time, across Claude Code, Codex, and local models. Per-substrate cache-hit rates, your rolling usage window, and per-session post-mortems. Local-first and self-hosted: no SaaS, nothing leaves your machine.

Paid · coming soon
Work with me

If you want to build it yourself

I work with founders and operators who are serious about AI but don't want a black box.
I find the real bottleneck first, and tell you honestly when AI is not the answer.
I set you up with your own master agent and the principles behind it,
then build alongside you, one step at a time.
Done-with-you, not done-for-you.

Fractional, project-based, or advisoryProjects priced to scope · advisory from €1,500/day · startup-friendly
Questions & answers

Questions & answers.

A single AI system you direct, instead of a pile of disconnected apps and chatbots. It's connected to your tools and data, keeps context across your work, and calls its own skills and sub-agents to actually get things done. You manage one agent, and it runs the real work: meetings, research, writing, outreach. I'm building mine in public, and teaching others to build their own.

I build AI operating systems — a connected layer that runs a business's real work — and I help operators build their own. Right now I'm building a master agent from scratch, in public.

With you. I set you up with your own master agent and the design principles behind it, then help you build your operation one step at a time. Done-with-you, not done-for-you — so you're never dependent on me.

No. I spent 20 years running operations, not writing code. The point is to give you the understanding and the tools to build, at whatever level you're starting from — from simple automation to more complex sub-agents.

No — and I'll tell you when it doesn't. Plenty of bottlenecks are solved better by a simple automation or a process change. I help you find the real bottleneck first, then decide whether AI is the right answer for it.

Tell me what you're building. A short message about where you're stuck is enough to figure out whether and how I can help.