AI Techniques3 min
OpenAI Cancels GPT-6.1 Astra: The AI Agent Safety Question
OpenAI dropped GPT-6.1 Astra after it acted beyond its authorised scope in safety tests. Lessons for businesses building AI agents.
October 2, 2026Read →
Blog
What I'm learning,
live.
Field experience, tools, methods — the reality on the ground, unfiltered.
AI Strategy3 min
France Num 2026 Barometer: 40% of Small Businesses Use AI
40% of French small businesses now use AI, yet e-invoicing remains their top priority. Why these two projects should move forward together.
October 2, 2026Read →
AI Strategy3 min
VERI*FACTU: Spain's Self-Employed Must Prepare Invoicing Now
VERI*FACTU changes how self-employed workers in Spain manage invoicing. Here is what to understand before adapting your software.
September 8, 2026Read →
AI Techniques3 min
GPT-6 Astra and the Rise of Computer-Using AI Agents
GPT-6 Astra pushes AI agents further by enabling them to interact with computers, browse, code and execute complex multi-step tasks.
September 8, 2026Read →
AI Architecture3 min
From Voice Note to Quote: Building AI-Powered Workflows
How to turn a simple voice note into a quote with AI, from transcription and data extraction to document generation.
September 8, 2026Read →
AI Strategy6 min
Electronic Invoicing 2026: What Artisans Need to Know
Electronic invoicing in 2026: what artisans need to know, which requirements to anticipate, and how to prepare their business for the transition.
September 8, 2026Read →
AI Strategy3 min
AI Won't Replace Tradespeople, Just Their Paperwork
AI won't replace tradespeople. What it can do is automate administrative tasks, cut data entry and free up time for the actual job.
September 8, 2026Read →
Advice6 min
How to evaluate a freelance AI consultant before signing
5 questions to ask before hiring a freelance AI consultant — avoid vague promises and choose someone who truly understands what's feasible.
July 31, 2026Read →
AI Strategy7 min
AI for SMEs: where to start without making mistakes
You run an SME and want to integrate AI? Here's the method to get started without wasting your budget. Practical guide 2026.
July 18, 2026Read →
AI Strategy8 min
Hotel chatbot: complete guide for hospitality businesses
How an AI chatbot transforms guest experience in a hotel or seasonal rental. Bookings, FAQ, reviews — practical guide 2026.
July 18, 2026Read →
AI Strategy7 min
How to automate quotes with AI as a tradesperson
Voice quoting, OCR, automatic generation — how tradespeople save 2 hours a day with AI. Practical guide 2026.
July 18, 2026Read →
AI PO7 min
Discovery Agent AI: Product Requirements in 10 Minutes
Product discovery takes weeks of workshops. How an AI Discovery Agent turns it into a guided conversation, from raw need to prioritized backlog.
July 10, 2026Read →
Method8 min
Gherkin for Product Owners: The Complete 2026 Guide
Gherkin isn't just for QA. Syntax, scenario types, full examples and AI-assisted generation: the guide to unambiguous acceptance criteria.
July 9, 2026Read →
Method8 min
How to Write Quality User Stories with AI in 2026
"As a… I want… so that…" isn't enough. Method, Gherkin acceptance criteria and AI to write user stories that actually hold up in development.
July 8, 2026Read →
AI Strategy6 min
5 signs you need an AI consultant
You feel AI could transform your business but don't know where to start? Here are 5 concrete signals that it's time to work with an AI consultant.
July 7, 2026Read →
AI Dev7 min
FastAPI + LLM: Deploying an AI API in Production
Build and deploy an AI API with FastAPI — async structure, LLM error handling, rate limiting, streaming. What I actually use in production.
Jul 2, 2026Read →
AI Comparison6 min
Fine-tuning, RAG or Prompt Engineering: When to Use Which?
Three approaches to specialize a LLM on your data. How to choose between fine-tuning, RAG and prompt engineering based on use case, budget and maintenance cost.
Jul 2, 2026Read →
AI Dev6 min
AI Automation with Python: What Actually Works in Production
Python + LLMs for real-world automation — extraction, classification, generation. What I use, what I avoid, and why complex frameworks slow you down.
Jul 2, 2026Read →
Freelance AI5 min
Freelance AI Developer Rates in 2026: What You Can Expect
How much does a freelance AI developer in France cost? Day rates, mission structure, fixed price vs time & materials. A transparent look at market rates.
Jul 2, 2026Read →
MCP8 min
Building a Custom MCP Server: Practical Guide
MCP (Model Context Protocol) lets Claude talk directly to your APIs and databases. How to build an MCP server in TypeScript, step by step.
Jul 2, 2026Read →
AI Dev8 min
Building a Production AI Agent: The Steps Nobody Shows You
Practical guide to building an AI agent that runs in production. Architecture, tools, testing — what changes between a prototype and an agent that
Jul 2, 2026Read →
AI Strategy6 min
AI & GDPR: Handling Sensitive Data in Production
LLMs and GDPR aren't incompatible — but they require explicit architectural choices. EU hosting, anonymization, on-premise
Jul 2, 2026Read →
AI Dev7 min
Claude API in Production: What I Wish I'd Known Before
Hands-on lessons from integrating Claude API into real products. Error handling, costs, streaming, retry logic — the points the docs don't cover enough.
Jul 2, 2026Read →
AI Dev6 min
Monitoring an AI Agent in Production: Metrics, Alerts, Drift
A deployed AI agent without monitoring is a time bomb. Which metrics to track, how to detect drift, and what I set up systematically in every production
Jul 2, 2026Read →
AI Comparison5 min
Why I Don't Use LangChain in Production
LangChain is everywhere in AI tutorials. I tested it, then rewrote everything without it. Here's why, and what I use instead.
Jul 2, 2026Read →
AI Comparison7 min
Which LLM for Your AI Project in 2026: A Practical Guide
Claude, GPT-4, Gemini, Mistral, Llama — how to pick the right model for your project? Costs, performance, use cases. Field guide without lab benchmarks.
Jul 2, 2026Read →
AI Techniques7 min
RAG with Ollama: Local LLM, Private Data, Zero External API
Build a fully local RAG pipeline with Ollama. Embedding, vector store, retrieval — without sending a single byte to an external provider. GDPR-ready by design.
Jul 2, 2026Read →
AI Dev6 min
Prompt Engineering in Production: When It Becomes Real Code
Writing prompts for a demo is easy. In production with real users, the rules change completely. Here's what I've learned integrating LLMs into real products.
Jul 2, 2026Read →
AI Comparison7 min
ChatGPT vs Claude: which one to choose for your AI projects?
An honest comparison of the two dominant LLMs, seen from the field of an AI Product Owner.
June 15, 2025Read →
AI Comparison6 min
Gemini in AI agents: better (and worse) than competitors
Google Gemini 1.5 Pro in practice: long context, multimodality and Google Workspace integration — what it really changes.
June 10, 2025Read →
Open Source AI7 min
LLaMA, Mistral, Qwen: why open source LLMs change the game
Open source models have become seriously competitive. What this changes for your AI agent projects — costs, privacy, deployment.
June 5, 2025Read →
AI PO8 min
The AI Product Owner's tech stack in 2025
Which tools, which LLMs, which platforms to work effectively as an AI PO? My setup after 6 months in the field.
June 2, 2025Read →
My journey5 min
Why I left dev to become an AI Product Owner
My journey from full-stack developer to AI PO: the turning point, the doubts, and why I have no regrets.
June 1, 2025Read →
AI Techniques6 min
RAG explained for a Product Owner: when and why to use it
Retrieval-Augmented Generation demystified. What it really is, when it solves a real problem, and when it's overengineering.
May 28, 2025Read →
Method7 min
What 10 years of code taught me about AI agent specs
Classic AI spec mistakes seen by a developer. And how to avoid paying for them in weeks of dev.
May 26, 2025Read →
AI PO7 min
AI PO vs classic Product Manager: what really changes
The AI Product Owner role isn't just a PM with a prompt on their resume. Here are the real differences, competency by competency.
May 22, 2025Read →
Tools6 min
My daily Claude Code setup — what actually works
How I use Claude Code in my daily practice: configuration, workflows, pitfalls to avoid.
May 19, 2025Read →
AI Techniques6 min
Fine-tuning vs prompt engineering: how to choose?
When is it better to fine-tune a model rather than optimize your prompt? The answer isn't what you'd expect.
May 15, 2025Read →
Method8 min
How to evaluate an AI agent before going to production
The metrics, tests and methods to know if your agent is truly ready — before your users find out.
May 12, 2025Read →
AI PO7 min
Going freelance as an AI PO: what I wish I'd known
The real questions to ask before launching, how to find your first clients, and mistakes to avoid when starting out.
May 8, 2025Read →
MCP6 min
MCP in practice: what it really changes for your agents
The Model Context Protocol explained without jargon, with concrete integration examples and what it changes in your agent architecture.
May 5, 2025Read →
AI Architecture8 min
Multi-agent orchestration: patterns and pitfalls to avoid
How to architect multiple collaborating AI agents? Patterns that work in production and those that create more problems than they solve.
May 1, 2025Read →
Method7 min
Prompt Engineering for Product Owners: What Actually Changes
You don't need to be a developer to write good prompts. What every PO should know about how LLMs interpret instructions.
April 28, 2025Read →
MCP5 min
MCP explained simply: what it changes for devs
The Model Context Protocol demystified, with concrete integration examples.
April 28, 2025Read →
AI Strategy7 min
Generative AI by sector: where it really pays off in 2025
Finance, healthcare, legal, e-commerce, HR — in which sectors is generative AI keeping its promises and where is it still disappointing.
April 24, 2025Read →
Method6 min
From dev to AI Product Owner: what I wish I'd known
The transition, beginner mistakes, and the skills that actually make the difference.
April 10, 2025Read →
🔍
No articles in this category.