Things that run without me.

I build AI systems that take on a task, use software tools to finish it, and check their own work.

Working on

Sending each request to the right agent with a small, fast model.

Evaluating agents, so a change can be checked before it ships.

Fine-tuning language and audio models for a specialized task.

Agents Models Delivery Product

Send a request

Pick something someone might ask for.

Turn a stack of scanned documents into data. Write tomorrow's post, and have it checked. Show the team whether the agent got better.

A small, fast model decides who takes it.

Models Read documents

A vision-language model reads each page and hands back structured data, whatever the document type.

Agents Write and review

One agent drafts, another reviews, and the cycle starts again the next day without anyone asking.

Delivery Test and evaluate

The agent runs against fixed checks, so a change is measured before it ships.

A sketch of how I think about routing. Nothing here is sent anywhere. The full list is under Can do.

Signal path

How the systems I build tend to flow. Hold the pointer over it to pause.

Trigger

A schedule or an event starts the work, so nobody has to ask.

Route In progress

A small, fast model picks the right agent.

Act

The agent uses tools to do the work.

Check

A review step looks at the result before it moves on.

Deliver

The result reaches a person or another system.

Can do

What I can build, and help decide to build, grouped by kind.

Agents

Software that acts, not only answers.

Start on their own

Agents that begin work on a schedule or when something happens, so nobody has to ask.

Write and review

Agents that draft content and agents that review it, on a daily cycle.

Route requests

In progress

Sending each request to the right agent with a small, fast model.

Build workflows

An agent that creates business-process diagrams, with tools it can call to assemble the workflow.

Serve many customers

Helped design a platform where many customers run their own agents, kept apart.

Models

Models that read, search, and listen.

Read documents

A modular system that turns documents into structured data with vision-language models, across document types and in batches.

Find answers

Worked on the retrieval and search behind question-answering products.

Train and measure

Fine-tuned and benchmarked language and audio models for specialized tasks, including distributed training.

Delivery

Getting it to people, and keeping it honest.

Ship the interface

Dashboards, internal tools, and web apps for AI services, backend included.

Run on your own machine

Tuned an agent to run entirely on a local computer, text recognition included, and to respond sooner.

Test and evaluate

In progress

Built the tools a team uses to test and develop agents. Now building a pipeline to evaluate them.

Product

The stage before building: deciding what to make, and what to leave out.

Find the real problem

Turning a rough idea into a specific problem: who has it, how they cope today, and what better would look like.

Shape the first version

Deciding what the first version does, and what it leaves out.

Pick what to test first

Choosing the cheapest thing that shows whether an idea works, before the whole product is built.

Fit it to what AI can do

Matching an idea to what current models do well, what it will cost to run, and where they are heading.

Good at

Each one rests on something I have done.

Keeping cost in view

Treats what an AI service costs to run as part of the design, not an afterthought.

Checking before trusting

Builds the tests and reviews that sit around an agent, not only the agent.

Helping a team do its best work

Coordinates the work, coaches people, and keeps a small team pointed the same way.

Design sense

Cares how a product looks and reads, not only how it works.

Likes

What I keep coming back to.

Token economics

What thinking costs

Every model call costs money and time. I like working out where that spend pays off and where it does not.

Agent harnesses

The part around the model

A model alone does little. The tools, memory, limits, and checks around it decide whether it is useful. That is the part I like building.

AI development trajectory

Where this is going

I follow where model ability is heading and what it changes for the products built on top.

Product ownership

Owning the whole thing

I like carrying a product from the first idea to the person using it.

Startups

Early companies

Small teams, short feedback loops, and a first version in front of real people early.

Benchmarks

Problems with a scoreboard

A clear score and a clock keep a problem honest. I like work that can be measured that way.

Contact

Have something that should run on its own, or an idea to shape? Write to me.

Email ••••••••

Profile ••••••••

Things that run without me.

Can do

Start on their own

Write and review

Route requests

Build workflows

Serve many customers

Read documents

Find answers

Train and measure

Ship the interface

Run on your own machine

Test and evaluate

Find the real problem

Shape the first version

Pick what to test first

Fit it to what AI can do

Good at

Keeping cost in view

Checking before trusting

Helping a team do its best work

Design sense

Likes

What thinking costs

The part around the model

Where this is going

Owning the whole thing

Early companies

Problems with a scoreboard

Contact

Reading as an agent? Start with llms.txt.