Choose what to learn next.
Three ordered reading paths, with prerequisites and a concrete outcome. Choose a goal, follow the first three readings, then explore the full collection.
Get started with Claude Code
6 publishedUse AI-assisted engineering on real work without giving up understanding or control.
Before you start: Basic command-line and Git experience. No previous agent setup required.
What you will work towards: Configure a first workflow and understand the changes you accept.
- 01 / Article
Choose your AI-assisted engineering starting path →
Choose between Claude Code and Cowork, then follow the Start, Build, or Scale path that matches your role and current operating problem.
- 02 / Guide
Claude Code setup, level by level →
Three configuration layers for project context, daily tools and persistent memory, with checks for what loads and how it behaves.
- 03 / Article
UVAL: the protocol I built to stop accepting code I don't understand →
Jeremy Twei coined it. Addy Osmani popularized it. Margaret-Anne Storey extended it to teams. Here's what I built to fight all three.
Go Further in the Claude Code Guide
Practical resources selected to help you take the next step.
Browse all 6 readings in Start
Claude Code setup, level by level
1/6 · Opposite AI results: what context can explain
Claude Code under the hood
Choose your AI-assisted engineering starting path
Non-technical to production in 10 days with Cursor AI
UVAL: the protocol I built to stop accepting code I don't understand
Make agent workflows reliable
19 publishedTurn individual practice into repeatable workflows, context, and verification.
Before you start: An existing coding-agent workflow and a repository you can experiment with.
What you will work towards: Structure context, verification and human review around real development work.
- 01 / Guide
Context engineering: the L0-to-L5 playbook →
Choose context controls from L0 to L5 according to the failure you observe, from project documentation to scoped rules, behavior checks and shared configuration.
- 02 / Article
From afterthought to infrastructure: how AI config evolves in a real project →
Nine months of AI configuration in one production project: evolving responsibilities, profile-based generation and a measured reduction in always-on lines.
- 03 / Article
UVAL: the protocol I built to stop accepting code I don't understand →
Jeremy Twei coined it. Addy Osmani popularized it. Margaret-Anne Storey extended it to teams. Here's what I built to fight all three.
Go Further in the Claude Code Guide
Practical resources selected to help you take the next step.
Browse all 19 readings in Build
Coding faster moves the cost to verification
When an independent reviewer earns its place
Designing a bounded review loop
How to read a token-compression benchmark
Jev : comprendre, comparer et tester le modèle de TypeSafe
Jev: understand, compare and test TypeSafe's model
2/2 · Claude selected my output style. Then ignored it
1/2 · Why I combined three Claude Code skills
Portable agent configuration is a release system, not a shared folder
Your CLAUDE.md is too long
Context engineering: the L0-to-L5 playbook
MCP servers: what they actually cost and when to use them
TDD with Claude Code
6/6 · Portability becomes a Scale concern
3/6 · Mapping the token-reduction toolbox
2/6 · Diagnose and repair context drift
Claude is my second contributor: what real Git stats show
From afterthought to infrastructure: how AI config evolves in a real project
AI velocity is bidirectional
Build shared team practices
25 publishedMake AI-assisted engineering reliable, governable, measurable, and sustainable across teams.
Before you start: Experience using agents and responsibility for shared engineering practices.
What you will work towards: Connect team instructions, delivery practices and cost decisions.
- 01 / Article
Lean and AI: follow the work until it reaches the user →
AI can speed up one step while the request waits elsewhere. A practical way to map the full service, protect quality and measure accepted user outcomes.
- 02 / Article
5/6 · The AI instruction system is a product, not a config file →
Personal CLAUDE.md to team AI instruction system for six engineers. How Méthode Aristote separates sources, shares modules, and catches behavioral drift in CI.
- 03 / Article
FinOps applied to tokens: who owns the AI bill →
Cloud FinOps put a cost study first and a named owner for the number second. Three practitioner cases show that sequence applied to token bills.
Go Further in the Claude Code Guide
Practical resources selected to help you take the next step.
Browse all 25 readings in Scale
5 AI code reviewers, 1 repository, and what developers did next
Testing Opus 5.5 as the code-review baseline
Turn recurring review comments into tested controls
A green review is not a merge gate
Operating a multi-reviewer system safely
Du code au merge : organiser le travail des agents en équipe
From code to merge: organizing agent workflows as a team
Lean and AI: follow the work until it reaches the user
A $214 AI coding agent rewrite
Doctolib's cross-verified AI adoption data
FinOps applied to tokens: who owns the AI bill
Measuring your own AI usage: three meters, three different answers
Price per token is incomplete: why cheaper models don't mean cheaper bills
AI coding productivity: why one gain is not your forecast
Why AI ROI stays invisible, even to the people measuring it
You cannot depend on a single AI vendor
Moving the memory observer to a local model: five constraints nobody documents
Une seule source configure Claude Code et Codex
One source configures Claude Code and Codex
Back Market a sorti 245 développeurs d'Anthropic en direct
Back Market moved 245 developers off direct Anthropic access
Persistent memory: the six failures that never raise an error
Plan-execute: running 20+ agents on a migration
Claude Code security: the attack surface few teams audit
5/6 · The AI instruction system is a product, not a config file
Perspectives
7 publishedExamine how AI changes engineering careers, organizations, infrastructure, markets, and society.
Perspectives is not a maturity level. It is where technical practice meets careers, organizations, infrastructure, markets, and society.
Go Further in the Claude Code Guide
Practical resources selected to help you take the next step.
These resources provide adjacent lenses. They are not maturity stages.