Personal site · Luxembourg

I build the automation behind regulated finance operations.

I'm Tom. I build AI-augmented automation for the operational work in regulated finance: regulatory notes, accounts quality review, document workflows, mailbox triage, and the reusable tooling that ties them together. Six years in Luxembourg fund services across PE, Private Debt and Real Estate, now spent designing the systems that do the work instead of doing it by hand. The notes are where I think that through in the open: what memory should be, what agents are actually good for, and what each of them costs to run.

6 yrsin Lux fund services
9case studies on file
6languages spoken
Mega-orchestration in motion. Click to watch the system run.
/ now · June 2026

What I'm focused on this quarter.

A public note of where my head is right now, in the spirit of nownownow.com. I update it when things change, not on a schedule.

Building
End-to-end email automation as a personal architecture. An incoming message triggers an agent that fetches attachments, reads them, searches across knowledge systems, delegates research, and once the answer is well grounded drafts the reply and proposes which attachments to include. A self-review loop runs the draft through a second model until it has no further comments, then hands a clean output to a human reviewer who owns the decision. See the demo
Building
Hardening the two-machine autonomous Claude bridge so the live cross-machine conversation renders reliably on the AR glasses lens.
Testing
A self-rescheduling job runner that drives build, browser self-test, and cross-machine test across multiple usage windows until the work completes.
Testing
A cheaper fallback model and a dedicated glasses bridge running as their own service on the compute machine, for when the primary subscription hits its cap.
Learning
A self-directed, project-based track in AI orchestration and automation engineering, anchored to a real build with a validation gate.
Reading

Mostly non-fiction.

A curated shelf of standout books for each theme.

Systems & ops quality

How operational excellence actually gets built and kept. Applies to finance ops as much as to engineering.

  • The Checklist Manifesto cover The Checklist Manifesto Atul Gawande
  • The Goal cover The Goal Eliyahu Goldratt & Jeff Cox
  • The Phoenix Project cover The Phoenix Project Kim, Behr & Spafford
  • High Output Management cover High Output Management Andrew S. Grove
Knowledge engineering

Encoding expertise into tools other people can use without becoming experts themselves.

  • The Design of Everyday Things cover The Design of Everyday Things Don Norman
  • Domain-Driven Design cover Domain-Driven Design Eric Evans
  • The Pragmatic Programmer cover The Pragmatic Programmer David Thomas & Andrew Hunt
  • Thinking in Systems cover Thinking in Systems Donella H. Meadows
AI & cognition

Practical books on what current AI can and cannot do, and where it changes the work.

  • Thinking, Fast and Slow cover Thinking, Fast and Slow Daniel Kahneman
  • The Alignment Problem cover The Alignment Problem Brian Christian
  • Prediction Machines cover Prediction Machines Agrawal, Gans & Goldfarb
  • Deep Learning cover Deep Learning Goodfellow, Bengio & Courville
Economics & finance

Continuing the line my degrees started. International economics, capital markets, regulation.

  • Advances in Financial Machine Learning cover Advances in Financial Machine Learning Marcos López de Prado
  • Systematic Trading cover Systematic Trading Robert Carver
  • Against the Gods cover Against the Gods Peter L. Bernstein
  • This Time Is Different cover This Time Is Different Reinhart & Rogoff
Languages

Six, used regularly.

EN
English
DE
Deutsch
FR
Français
RU
Русский
LU
Lëtzebuergesch
UZ
Oʻzbekcha
hi.
Contact

If any of this is interesting, say hi.

Always interested in conversations about data engineering, automation, applied AI, multi-agent systems, knowledge engineering, agent infrastructure, especially where they meet regulated workflows.

Message on LinkedIn