Artificial Intelligence

From factory to intelligence : What survives contact with a regulator

Post 3 of 8 in the series on rebuilding a bank’s software development factory for the agentic era. Block’s “From Hierarchy to Intelligence” is the most interesting organisational design published this year, and roughly half of it is illegal to implement in a supervised European credit institution. That sounds like a complaint. It is not.…

Artificial Intelligence

From factory to intelligence : The AI token bill

Post 2 of 8 in the series on rebuilding a bank’s software development factory for the agentic era. The AI token bill : This is the post I would have wanted to read eighteen months ago, so I am putting it second rather than burying it in the middle of a design series. Here is…

Artificial Intelligence Software Design and Architecture

L’usine de développement logiciel fonctionne toujours, c’est la contrainte qui a bougé

Article 1 sur 8 de la série consacrée à la refonte de l’usine de développement logiciel d’une banque à l’ère des agents. Il y a 3 ans, j’ai publié ici un long guide sur la conception d’une usine de développement logiciel pour une banque. 9 chantiers, Team Topologies, les capacités Accelerate, les métriques DORA, une…

Artificial Intelligence Software Design and Architecture

From factory to intelligence: The Software Factory still works, but the constraint moved

Post 1 of 8 in the series on rebuilding a bank’s software development factory for the agentic era. 3 years ago I wrote a long guide about designing a software development factory for a bank. 9 streams, Team Topologies, the Accelerate capabilities, DORA metrics, an IT-GOV function holding the control catalogue, and a fictional composite…

Artificial Intelligence

Computer Use: WHY? WHAT? HOW?

Compuer Use in 2026: what ships, what breaks, what it costs A practitioner’s guide to agents that drive software the way people do, with a benchmark of what actually works in September 2026. Two years ago, “computer use” was a demo. A model took a screenshot, clicked something, and everyone applauded because it worked once.…

Artificial Intelligence

GPT-6 Astra: What actually changes for engineering teams

OpenAI shipped GPT-6 Astra on 3 September 2026, four weeks after saying it had slowed the release over cyber risk. Greg Brockman told reporters he personally believes the company has reached AGI. That framing will dominate the discourse for about a fortnight and then evaporate. Underneath it there is a real release with real consequences…

Artificial Intelligence

WebMCP : le Pourquoi?, le Quoi?, le Comment?

Google a proposé WebMCP. OpenAI l’a livré en premier. WebMCP permet à une page web de tendre à un agent une fonction plutôt qu’un bouton. Un site enregistre des tools nommés, en JavaScript ou en HTML, chacun avec une description et un JSON Schema en entrée, et un agent qui tourne dans le navigateur peut…

Artificial Intelligence

WebMCP: the Why?, the What? and the How?

Google proposed WebMCP. OpenAI shipped it first. WebMCP is a way for a web page to hand an agent a function instead of a button. A site registers named tools in JavaScript or in HTML, each with a description and a JSON Schema for its inputs, and an agent running inside the browser can list…

Artificial Intelligence

Ce qui doit rester dans AGENTS.md, et ce qu’il faut en sortir

Mon fichier AGENTS.md faisait 340 lignes. Je sais très bien comment j’en suis arrivé là. L’agent faisait quelque chose qui ne me plaisait pas, j’ajoutais une règle, et j’ai répété l’opération pendant des mois. Personne n’a jamais rien supprimé, et deux des règles se contredisaient. Ce fichier entre dans chaque session, avant le premier token…