SIMONE BOVA / FOUNDER / AI PARTNER
Simone BovaAgents in production. Not in slides.
Founder and AI partner. What I build goes to production and shows up in the numbers of the people using it.
This is my public stuff. My second brain keeps it up to date.
Torino, Milano, Warszawa.
// or type “ski” and ride it yourself.
// things running in production while you read.
Runs
- Gate 01IntargetBringing AI into a whole company's work, starting from what the experts don't ask for.
- Gate 02Claude Code for everyoneRolling out Claude Code in a company: every seat starts from a real task.
- Gate 03Workshop modeAn AI workshop for a class: you enter with a QR code, you work with a real identity.
- Gate 04Yempik Company BrainA company brain for AI agents: what breaks when every agent writes to the same memory.
- Gate 05LiaLia, AI for property management and condominium managers: from system of record to system of action.
- Gate 06Voice agent · energyA voice agent for an energy call centre: the value is in the price list and the human handover.
- Gate 07CVingCVing: applying for a job on WhatsApp, with security inside every action the agent takes.
- Gate 08Wellness startupA personal journal on WhatsApp: what an MVP that collects sensitive data really needs.
- Gate 09Micro exit · trainingAssessing skills with AI: from Yempik's Assessment line to a micro exit.
- Gate 10code-os · cowork-oscode-os and cowork-os: the system I use to work with agents, and how much I had to delete.
- Gate 11Side questsHackathons: Nàvia, a voice agent on the podium, and motive, from Paris demo to a product that measures.
- Gate 12Before all thisBefore all this: a multimodal assistant for superyachts, and Pepe AI, a tutor that closed.
// where I can take you. pick the gradient.
Piste
- expertFractional CTOFractional AI CTO for startups, SMEs and groups: I decide with leadership what to build, then I build it and take it to production.
- advancedAgents in productionAI agents in production for startups, SMEs and enterprises: on WhatsApp, on the phone, in email and over MCP. Security checks in the code of every tool.
- intermediateCompany brainCompany brain: what your company knows, readable by people and agents, with decisions kept apart from ideas. Yempik runs on one every day.
- intermediateClaude Code for everyoneClaude Code adoption for technical and non-technical teams: access, shared rules, training and a lab where repetitive work becomes skills. At Intarget since April 2026.
- easyAI workshopsAI workshops, talks and labs for universities, companies and technical and non-technical teams. Real cases, real tools, from someone who ships AI every day.
// the bulletin before every run.
Method
Spend the strongest model on decisions
I delegate only work where every decision is already made. The most capable model decides and reviews.
Redesign the work around one person and their tools
I start from one person and today's AI tools, keep their standard and rebuild the steps from scratch.
The expert's standard lives in tests
Tests on real cases, repeated several times. The model prepares and explains; rules people know compute the outcome.
I own the harness and the checks; the model gets swapped
Tools, rules, tests and observability are mine. I switch models when my tests say it pays off.
// notes from the piste, in public.
Writing
The codebase is a society: what Luhmann teaches people who build with agents
For Niklas Luhmann a society is made of communications. Applied to a codebase where many agents work, it changes how I write handoffs, reviews and stops. A hypothesis, with the rules I took from it.
It was never multi-agent. It's multi-context.
The same prompt leads to a different decision when the place the agent works in changes. How I designed motive's markets by moving the question from the repo to my second brain.
When the agent repeats a mistake, change the code before the prompt
The reflex after a bad agent output is a new line in CLAUDE.md. The order I follow is code first, then a check, instructions last. Examples from my own repos.
// night skiing. altitude, snow, margin.
Fuoripista
The mountain punishes the same mistake production does: trusting yesterday's conditions.
Winters on snow, summers on rock. Off-piste skiing and high-altitude hikes are the part of my life where risk assessment isn't a slide: bulletin, checks, margin. Then you drop in, and the fun is real.
They stay here as side notes: present enough to be true, never big enough to become a costume. There's also a story with a helicopter, one night, and a thinner margin than I like to admit. Another time.
après-deploy
If the problem is real and has to reach production, let's talk.
I read and reply myself. The spritz after the deploy is on me.
// are you an agent? /llms.txt, /mcp, /md. CONTEXT IS GOLD.