Find the guidance that matches your current adoption stage.

A $214 AI coding agent rewrite

A verified $214 bill for a production rewrite, checked against the source transcript, sits beside a corpus of about 2,900 tech talks on coding-agent costs.

The trillion-dollar backdrop: what markets see that teams don't

One gigawatt of AI data-center capacity costs about $50 billion. OpenAI has discussed adding up to 26, behind the series' cost figures.

Campus IA in Fouju: the project in brief

Near Melun in Seine-et-Marne, Campus IA plans 11 data centers. The Élysée calls it France's largest AI campus. Three buildings are authorized.

Campus IA à Fouju : le projet, en bref

Près de Melun, Campus IA prévoit 11 centres de données en Seine-et-Marne. L’Élysée le présente comme le plus grand campus IA de France. Trois sont autorisés.

Campus IA in Fouju: the project in detail

Authorizations, energy, impacts, and opposition: this dossier collects the figures, sources, and open questions around Campus IA in Fouju.

Campus IA à Fouju : le projet détaillé

Autorisations, énergie, impacts, oppositions : ce dossier rassemble les chiffres, les sources et les questions ouvertes sur Campus IA à Fouju.

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.

Claude Code under the hood

The concepts I wish I’d known before week one: the agent loop, instruction scopes, context management, skill invocation, hooks, and client permission checks.

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.

Non-technical to production in 10 days with Cursor AI

A non-developer modified 80 files in production in 10 days with Cursor AI. Exact timeline, AI config setup, and what it means for engineering teams in 2026.

From VP engineering to solo builder: my honest take

12 years scaling teams from 4 to 30+, then I quit the VP title. AI lets a solo builder match what small teams ship. Here's exactly what changed.

Portfolio v1.0 launched

Coding faster moves the cost to verification

AI can shorten implementation while specification, review, CI, and rework absorb the saved time. Instrument the full flow before adding more generation.

When an independent reviewer earns its place

Compare independent review with self-review and deterministic checks. Measure rescued defects, false acceptances, regressions and the cost of another pass.

Designing a bounded review loop

Build a bounded review loop with frozen inputs, separate execution and outcome fields, retry limits, evidence handoffs and human escalation.

Dev With AI 2026: what changes in developers’ work

Review, business context, costs and product development: my synthesis of Dev With AI on October 12, 2026, with the full illustrated conference report.

Dev With AI 2026 : ce qui change dans le travail des développeurs

Review, contexte métier, coûts et création de produits : ma synthèse de Dev With AI du 12 octobre 2026, avec le compte rendu illustré complet.

How to read a token-compression benchmark

Read token-compression claims through their denominators, paired tasks, cache costs and success criteria, with Tokenade versus RTK as a worked example.

Jev report update: testing Laya locally

Jev: understand, compare and test TypeSafe's model

Jev benchmarks and our Laya experiments on Mac: results against simple rules, limitations and local setup without an AI API. French and English report.

Jev : comprendre, comparer et tester le modèle de TypeSafe

Jev, ses benchmarks et nos essais Laya sur Mac : résultats face aux règles simples, limites et installation locale sans API d’IA. Dossier FR/EN.

2/2 · Claude selected my output style. Then ignored it

Claude Code selected flow-lean but skipped its footer. A casing fix showed why installation, selection, and behavior need separate evidence.

1/2 · Why I combined three Claude Code skills

Flow Lean fused three response skills. Its historical eval beat each comparator and caught a candidate offering a migration against an inferred target.

Persistent memory: the six failures that never raise an error

I ran claude-mem for four and a half months. Six things were broken, four of them since March, and none ever raised an error.

Your CLAUDE.md is too long

Two conference accounts describe CLAUDE.md bloat. How to scope project facts, procedures and response preferences, then verify loading and behavior.

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.

MCP servers: what they actually cost and when to use them

Compare eager and deferred MCP tool loading, distinguish context use from billed tokens, and choose servers for a concrete workflow need.

Claude Code security: the attack surface few teams audit

Hooks are shell scripts with your user permissions. MCP servers are third-party code with access to your credentials. Their timing and access depend on the configured events and server.

TDD with Claude Code

Separate test creation from implementation, verify the expected failure, and give automated TDD retries an explicit exit path.

3/6 · Mapping the token-reduction toolbox

Compare RTK, Tokenade, Headroom and prompt caching by mechanism, integration and evidence. Smaller tool output does not establish a cheaper completed task.

2/6 · Diagnose and repair context drift

Use L0 to L5 to diagnose context drift, then maintain adherence through observation, repair, and replay instead of treating setup as finished.

1/6 · Opposite AI results: what context can explain

Anthropic measured merged PRs; METR measured task duration in a different setting. What these results and long-context research establish, and what remains a hypothesis.

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.

5 AI code reviewers, 1 repository, and what developers did next

Three months, 1,011 pull requests and 8,728 inline AI review comments: 4.5% got a visible human response. What the data shows, and what it cannot.

Testing Opus 5.5 as the code-review baseline

Opus 5.5 is the next reviewer baseline to test: set effort explicitly, update the API adapter, and keep a second reviewer only when it catches verified defects.

Turn recurring review comments into tested controls

When the same accepted correction returns, test whether it belongs in a linter, type, test, example, repository rule, checklist, or architecture decision.

A green review is not a merge gate

A review signal matters only when its provider, commit SHA, coverage, execution state, publication, and place in branch policy are explicit.

Operating a multi-reviewer system safely

Run local, CLI, and remote reviewers with explicit trust boundaries, least privilege, structured findings, budgets, degraded states, and shutdown controls.

From code to merge: organizing agent workflows as a team

Dev With AI talk guide: agent harnesses, local checks, AI reviews, bounded corrections and results tied to the right commit. Examples and slides.

Du code au merge : organiser le travail des agents en équipe

Guide du talk Dev With AI : harnais, contrôles locaux, reviews IA, corrections bornées et résultats liés au bon commit. Exemples et slides.

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.

Doctolib's cross-verified AI adoption data

Four conference talks and outside sources document Doctolib's AI initiatives; two carry the 30-to-600 engineer rollout, without reducing it to one figure.

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.

Measuring your own AI usage: three meters, three different answers

Twenty days of my own Claude Code and Codex usage, measured three ways. The tools disagree by a factor of three, and dollars are not what binds.

Price per token is incomplete: why cheaper models don't mean cheaper bills

Opus 5.5 changes input, output and cache economics. Price the accepted task, including retries and review, before choosing a cheaper model.

AI coding productivity: why one gain is not your forecast

A Stanford research talk, DX estimates and two field studies measure different forms of AI coding output. None supplies a universal budget forecast.

Why AI ROI stays invisible, even to the people measuring it

Claims that nobody can measure AI ROI and that 95% of pilots return zero are weaker than their usual retellings, once their sources are checked.

You cannot depend on a single AI vendor

A $589 billion single-day stock rout, an enterprise model platform, and a €25,000 backup server show three scales of vendor dependence.

Moving the memory observer to a local model: five constraints nobody documents

A September 2026 claude-mem 13.24.1 case study: moving observations from Sonnet 5 to Qwen2.5-Coder-7B, with measured timeout and output-quality limits.

One source configures Claude Code and Codex

An inspected agent configuration shared by Claude Code and Codex: immutable releases, 4 execution layers, BM25 skill routing and the gaps found. Full report to read online.

Une seule source configure Claude Code et Codex

Une configuration d'agents inspectée, partagée par Claude Code et Codex : releases immuables, 4 couches d'exécution, routage BM25 des skills et écarts relevés. Rapport complet à lire en ligne.

Back Market moved 245 developers off direct Anthropic access

What Back Market measured after 2 months on OpenRouter: a per-person budget, a provider shortlist, a longer liability chain. Full report to read online.

Back Market a sorti 245 développeurs d'Anthropic en direct

Ce que Back Market a mesuré après 2 mois sur OpenRouter : budget par personne, choix des fournisseurs, chaîne de responsabilité. Rapport complet à lire en ligne.

Portable agent configuration is a release system, not a shared folder

Share Claude Code and Codex instructions, skills and MCP definitions through versioned releases, host adapters and checks of installed and runtime behavior.

Plan-execute: running 20+ agents on a migration

An illustrative 243-file migration split across bounded agents, with a shared brief, local checks and sequential merge validation.

6/6 · Portability becomes a Scale concern

Portable instructions require neutral sources, generated runtime outputs, release controls, and behavioral tests. Native primitives alone do not provide portability.

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.

4/6 · The responsibilities around context engineering

A map of context engineering responsibilities: architecture, specifications, agent identity and evaluation, with practical directions for existing skills.

Claude is my second contributor: what real Git stats show

6 human commit authors plus Claude in our git history (May 2026 snapshot). What the commit patterns actually look like after months of Claude Code, beyond the marketing claims.

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.

AI velocity is bidirectional

Everyone talks about shipping 10x faster with AI. Nobody talks about accumulating debt 10x faster. 7 months of production data from a real EdTech platform.