Method · Understand to decide
Guides
Clear guides on AI and the tools I use: what they are, what they're for, what they change. Written for busy merchants and decision-makers who want to get up to speed fast — but readable at any level. Three reading depths in every page: in 30 seconds, the main body, and going further.
★ · Latest
Latest guides
Case study · July 13, 2026
A competitive price dashboard, built in-house
The competitor data (Wiser) was already in production, delivered by the integrator. The control layer — quoted at several weeks — built in-house with Claude Code in a few days. The most direct build vs buy case of the year.
Read the case study →
Case study · June 17, 2026
An agent that processes supplier invoices
It reads emails, extracts each invoice, links it to the right Odoo purchase order and pushes it into Teams. ~€2M of historical drift quantified — and a workflow that can no longer drift.
Read the case study →
01 · Understand
The basics
What we're actually talking about, jargon-free: AI, LLMs, Claude, and what all of this changes.
Guide 01 · May 31, 2026
What is AI, and what is an "LLM"?
Generative AI and LLMs without the jargon: what they do, who the big players are (OpenAI, Anthropic, Google, Mistral…), and what they can't do.
Read the guide →
Guide 02 · May 31, 2026
What is Claude, and why I built everything on it
Anthropic's assistant: the Opus/Sonnet/Haiku tiers, why it's at the top of the pack, and everything I run on it.
Read the guide →
Guide 03 · May 31, 2026
Why AI really changes the way you work
A shift on par with electricity: what changes for a leader (doing → directing), and what stays the same.
Read the guide →
Guide 07 · May 31, 2026
What is an "AI agent"?
An assistant responds, an agent acts — in a loop, until the job is done. What it enables, and the safeguard without which things go sideways.
Read the guide →
Guide 16 · June 10, 2026
Fable, Mythos, Glasswing: why Anthropic released two versions of the same model
On June 9, Anthropic launched Fable 5 — the first brick of a class above Opus — and restricted the unguarded version, Mythos 5, to vetted cyberdefenders. The story, jargon-free.
Read the guide →
02 · Tool up
Getting set up
The concrete building blocks for going from "chatting" to actually making AI act on your tools.
Guide 04 · May 31, 2026
Chat, Cowork or Code: which one to use
Three ways to use Claude depending on the task, the truth about the "terminal", and how to install Claude Code in one command.
Read the guide →
Guide 05 · May 31, 2026
What is GitHub, and why it's free and magical
The vault that backs up your work, keeps the full history, and once connected, deploys itself. For non-developers.
Read the guide →
Guide 06 · May 31, 2026
What is an "MCP", and how to connect Claude to your tools
Copy-paste, browser, API, MCP: the 4 ways to connect Claude to Shopify, Gmail, Drive… and why MCP changes everything.
Read the guide →
Guide 17 · June 10, 2026
What is a "loop"? Recurring agent tasks
An agent re-running the same task at a regular interval: monitor, check, alert — without you. Claude Code's /loop, how it differs from a scheduled task, and the guardrails.
Read the guide →
03 · Method
Working well with AI
The habits that make the difference between a "gimmick" and real time savings.
Guide 13 · May 31, 2026
How to talk to AI: writing a good prompt
A good prompt = 80% of the result. The recipe (context, task, format, constraints), the reflexes, and why iterating beats the "magic phrase".
Read the guide →
Guide 08 · May 31, 2026
Writing a good CLAUDE.md (the most valuable file)
The file that tells Claude how to work with you: tone, conventions, pitfalls. How to write it and help it grow.
Read the guide →
Guide 09 · May 31, 2026
The 4 principles I apply with AI (Karpathy-style)
Who Karpathy is, and 4 habits to make AI save you time: think first, keep it simple, stay surgical, steer by the objective.
Read the guide →
Guide 10 · May 31, 2026
Compound Engineering: your method improves on its own
Every lesson becomes a reusable rule: the compound interest effect applied to the way you work with AI.
Read the guide →
04 · Decide
For a leader or merchant
The strategic questions: high-ROI use cases, cost, data, visibility.
Guide 11 · May 31, 2026
AI in practice, for a merchant or SME
The use cases that pay off fast, without a tech team, seen from my store — and where to start.
Read the guide →
Guide 15 · May 31, 2026
How much does AI cost: subscriptions, API and a controlled bill
Everything is counted in tokens. The ways to pay (free, subscription, API, enterprise), which to choose, and how to keep the bill under control.
Read the guide →
Guide 12 · May 31, 2026
Is my data safe?
Where your data goes, who sees it, whether it's used to train models — and the simple habits (plan, settings, data sovereignty) to stay comfortable.
Read the guide →
Guide 14 · May 31, 2026
Being visible in AI: GEO explained
The SEO of the AI era: getting cited in ChatGPT, Perplexity or Claude answers. Why it matters and how to approach it.
Read the guide →
05 · Build in public
Case studies
Concrete and costed in time and money: how, without knowing how to code, I shipped a complete site and an AI watch bot in a weekend with Claude Code.
Dossier · June 14, 2026
Do you still need to buy an ERP when AI lets you build your own?
HF-OS: a press ERP built from scratch in 5 days / 96 PRs with Claude Code, plus Odoo extended at Cobra. CRM, ad sales, invoicing, dunning — and the real build-vs-buy question.
Read the dossier →
Guide · June 1, 2026
A site + an AI bot in a weekend?
The big question, in 3 reading levels: start from the need, pick the dumbest possible stack, separate concerns, set safeguards.
Read the guide →
Case study · July 13, 2026
A competitive price dashboard, built in-house
The competitor data (Wiser) was already in production, delivered by the integrator. The missing control layer — quoted at several weeks, left pending — was built in-house with Claude Code in a few days. The most direct build vs buy case of the year.
Read the case study →
Case study · June 1, 2026
Knowledge Hub: from idea to production
A complete static site (70+ pages, dark mode, GEO layer) in vanilla HTML/CSS/JS on GitHub Pages. Decisions, struggles, real time. Token cost: zero.
Read the case study →
Case study · June 1, 2026
AI Watch bot: from idea to production
A serverless agent: X/Twitter → Claude API → Telegram + site. 2-repo architecture, cross-repo bridge, CI struggles. Real cost ~a few cents/day.
Read the case study →
Making-of · June 1, 2026
Shipped in a weekend
The story, from a dinner with friends to "a beautiful baby shipped in 2 days". Without being a developer, in a duo with Claude Code.
Read the story →
The series grows over time. For the dated detail of what I'm building, head to the journal.