AI founder / mathematician / product thinker

I build systems that help ideas become real.

Product, AI, and writing shaped by curiosity, context, and craft.

Watercolor portrait of Alvis reading and thinking

Writing

Watercolor diagram of overlapping context layers feeding a central decision surface, illustrating context as product infrastructure.

The Context Layer Is the Product

Context shapes decisions, creates leverage, and compounds over time. The next durable AI products will treat context as infrastructure, not prompt decoration.

ContextAI systemsKnowledge work
Watercolor sketch of an agent loop with memory, tools, guardrails, and feedback arrows showing what production agents need beyond the demo.

Why Agent Demos Break in Production

Agent demos are optimized for spectacle. Production agents need memory boundaries, verifiable action, recovery paths, and a clear theory of when not to act.

AgentsReliabilityProvenance
Open the full notebook

About

I move between code, maths, and company-making to make complex ideas usable.

Read the longer story

Origin

Engineering instinct, research patience.

I like problems where the first answer is too neat: tools, systems, proofs, products, and the small loops that make them useful for people.

Method

Turn ambiguity into working shape.

My work usually starts with a sketch, a model, or a prototype, then tightens through careful feedback from the humans using it.

Bias

Build the thing that changes the conversation.

I care about software that makes hard ideas easier to hold, explain, test, and share so better futures become more practical.

Now

Current attention: context-aware agents, meaningful work, and the systems between them.

Building

Contexta: context infrastructure for agents that need memory, provenance, and accountable action.

Testing

AI-native workflows where virtual employees can own bounded work without hiding uncertainty from humans.

Writing

A thesis on meaningful work after automation: how people keep authorship when execution becomes abundant.

Learning

Complexity science, organizational design, proof systems, and architectural spaces that make thought feel embodied.

See the current operating note

Selected work

Projects around context, virtual employees, and purposeful work.

01

Contexta

A system for giving AI agents durable working memory, provenance, and context that can be inspected, updated, and trusted.

02

Amino.ai

An exploration of virtual employees: agents that can own bounded work, report progress, ask for judgment, and improve through feedback.

03

Work for Future

A research and product thread about meaningful work, career agency, and the tools people need to shape better futures.

04

Field Notes

A public notebook for mathematics, complexity science, design, architecture, and the emotional texture of building.

Explore the project map

Long-running threads

  • Applied mathematics
  • Developer tools
  • AI product systems
  • Research workflows
  • Company building

Contact

If the idea makes human work clearer, kinder, or more capable, I am interested.

[email protected]