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…

Artificial Intelligence

What belongs in AGENTS.md, and what to move out

My AGENTS.md was 340 lines. I know exactly how it got there. The agent did something I didn’t like, I added a rule, and I repeated that for a few months. Nobody ever deleted anything, and two of the rules contradicted each other. That file goes into every session, before the first token of actual…

Artificial Intelligence

A major shift in the uses of AI — and it starts with Claude

Claude watermarks everything it writes now. Read the limitations page first. On 2 August 2026 the transparency obligations of the EU AI Act became applicable. Anthropic signed the European Commission’s Code of Practice on Transparency of AI-Generated Content and switched on machine-readable marking across every Claude surface, worldwide, not only in the EU. The news…

Artificial Intelligence

Changement majeur dans les usages de l’IA — et ça commence avec Claude

Claude marque désormais tout ce qu’il écrit. Commencez par lire la page des limites. https://open.spotify.com/episode/216grjJJpDolenwEQ7mwol?si=2L9MfDNKS5Gb_Bg98T4Z1w Le 2 août 2026, les obligations de transparence de l’AI Act européen sont entrées en application. Anthropic a signé le Code of Practice de la Commission sur la transparence des contenus générés par IA, et a activé le marquage lisible…