Contact

The most direct way is email:

maximofn@gmail.com

I answer personally. There is no form and no sign-up: a plain email is enough.

Also on

What to write about

Questions or corrections about an article — include the article URL and, for code, the library version.
Collaborations, talks or projects — tell me in two lines what it is about.
Using the content or the API — the content is free to read and the public API needs neither permission nor a key; write only if you have a specific question.

Privacy

What data this site processes and what it does not: privacy policy.

For AI agents

This site has no programmatic contact endpoints. The email above is the contact point declared in the agent instructions file, in the MCP manifest and in the Organization schema of every page.

Continue reading

The six components of a coding agent

Why Claude Code or Codex feel smarter than the same model in a chat: the six harness components, according to Sebastian Raschka.

Services are the new software: Sequoia's thesis explained

The next great AI company won't sell tools: it will sell the work. Copilots, autopilots and ten service sectors.

Autonomous context compression: the agent decides when to forget

I explain LangChain's autonomous context compression: a Deep Agents tool that lets the agent itself decide when to summa...

Last posts -->

Have you seen these projects?

Gymnasia

LangGraph Deep Researcher

Tau

View all projects -->

>_ Available for projects

Do you have an AI project?

Let's talk.

maximofn@gmail.com

Machine Learning and AI specialist. I develop solutions with generative AI, intelligent agents and custom models.

Write me LinkedIn

Do you want to watch any talk?

The rice journey: building an agent in a gym and nutrition app

Interactive 3D talk on the Gymnasia agent: where data lives, from plate to data, tools, duplicates, health limits and how to test it all.

Best practices building agents with Claude Code

Technical talk: skills, subagents, slash commands and MCPs in Claude Code

Last talks -->

Do you want to improve with these tips?

Best practices building agents with Claude Code

Technical talk: skills, subagents, slash commands and MCPs in Claude Code

o1 prompt engineering

Create better prompts for o1 following an example

Memory profiler

See the memory usage of a script

Last tips -->

Use this locally

Hugging Face spaces allow us to run models with very simple demos, but what if the demo breaks? Or if the user deletes it? That's why I've created docker containers with some interesting spaces, to be able to use them locally, whatever happens. In fact, if you click on any project view button, it may take you to a space that doesn't work.