Lead with vision, build with teams.
Direction first, then the people, architecture, and rituals that turn it into delivery. The strongest AI work is a team sport.
Mathematics, AI, and the next decade of human work
Building AI that makes humans more capable, curious, and in control.
I believe the next era of technology belongs to people who pair mathematical clarity with creative ambition, and who treat education, leadership, and team-building as part of the engineering. This site is where I publish that work: agentic systems, applied AI, research, and writing, shaped by a decade of delivery and teaching.
- Mathematics as the foundation
- Creativity as the engine
- Education as the multiplier
Where the work meets
Mathematics, AI, and human creativity in service of practical work.
The site brings together agentic systems, applied AI, public products, and technical writing, all shaped by industrial delivery and teaching at scale.
What I believe
Five convictions that shape the work.
The site exists to put these beliefs into practice through products, research, writing, and teaching.
-
Technology should expand human capability, not replace it.
Systems are worth building when they leave people sharper, more curious, and more in control. AI should amplify judgment, not erode it.
-
Mathematics is how we stay honest.
Rigor before hype. Models that earn their conclusions, reasoning that holds up under pressure, and decisions that survive contact with reality.
-
Creativity is the real engine of innovation.
AI gets interesting when imagination, taste, and craft are in the loop. Vision sets the direction; technique gives it shape.
-
Education compounds everything.
What you can teach, you can build. What you can build, you can transform. Learning is how individuals, teams, and organisations stay alive to change.
-
Vision and teams turn ideas into change.
Leadership is the work of making ambition shippable, building the people, the architecture, and the discipline that move ideas into the world.
How the work happens
Vision sets the direction. Mathematics, teams, and teaching make it real.
Beliefs only matter if they translate into practice. These three habits carry the work from idea to shipped system.
Apply mathematical rigor to AI and data.
Models that earn their conclusions and systems that stay legible as they grow. Data science, agentic design, and evaluation grounded in clear reasoning.
Teach what we learn.
Writing, lecturing, and public work that turn experience into something others can use. Education and transformation are the same skill in different rooms.
Featured project
ZenInvest is the flagship open project on the site.
It brings together agentic design, deterministic controls, and human oversight in one of the hardest consumer AI domains: investing.
featured
ZenInvest
ZenInvest is an open-source investing system that brings screening, research, debate, and execution into one governed workflow. A three-model committee — Claude on strategy, GPT-4o as skeptic, Gemini on risk — researches and argues each idea with live tools, a proactive macro layer sets the market regime, and deterministic Python controls keep final veto power over capital. It runs autonomously cycle-to-cycle, but every cycle is pausable, auditable, and gated by hard rules no model can override.
Retail investors face information overload, fragmented workflows, and too many opaque tools. ZenInvest is designed to reduce that burden without pretending judgment can be outsourced.
Capability Tool use across market data, news, filings, and macro research sources
Capability Decision logging with audit trails and deterministic controls
Capability Cost-aware graceful degradation under enforced LLM budgets
Capability Full-stack delivery across backend, streaming APIs, and dashboard
Why it stands out
- Agentic architecture that stays inspectable
- Operator-supervised autonomy
- Learns only behind hard gates
- Technical product posture over return promises
About
The story behind the convictions.
I work where mathematics, AI, and human creativity meet, building AI systems in industry, writing about the work, and treating teaching as part of the engineering.
Read the full story From the lab
R&D briefs: agentic AI put under real constraints.
Short write-ups of the systems built in the lab — each one a testable idea, the engineering behind it, and the pattern worth reusing.
Can an agent get better without changing its weights?
ZenArena puts one of agentic AI's favourite claims — that memory makes agents better — under a falsifiable test, using chess and a Stockfish truth signal to measure whether governed memory beats remembering everything.
Agents advise, actuaries decide: an AI pricing engine a regulator could read
ZenRate wraps a deterministic actuarial core in a layer of collaborating AI agents — where exactly one agent holds a veto, every decision is recorded bi-temporally, and the compliance paperwork falls out of the architecture.
Forecasting as a loop, not a number on a slide
ZenForecast is an open-source, governance-first Python framework that treats forecasting as a continuous predict → decide → act → learn loop — with interchangeable models, leakage-free backtesting, and an audit trail behind a single API.