From NLP and data
to agentic AI.
NLP and machine learning at eXplain and Q°emotion, generative and agentic AI daily since 2025.
Currently AI Founding Engineer at Méthode Aristote, building open-source tools for developers in my spare time.
Editorial map
Choose the path that matches your next decision
Start, Build, and Scale describe adoption stages. Perspectives is a separate lens for broader changes in engineering and society.
- 01
Start
Use AI-assisted engineering on real work without giving up understanding or control.
- 02
Build
Turn individual practice into repeatable workflows, context, and verification.
- 03
Scale
Make AI-assisted engineering reliable, governable, measurable, and sustainable across teams.
Featured project cc-skill-usage Skill Analytics · Local-first · Observability
Separate lens
Perspectives
Examine how AI changes engineering careers, organizations, infrastructure, markets, and society.
RTK
82.2kCLI proxy that cuts the tokens in shell command output by 60-90%
Claude Code Ultimate Guide
6.1kClaude Code guide with 473 quiz questions, 13 bilingual whitepapers and 58 recap cards per language. PDF and EPUB editions updated September 26, 2026 (v3.43.0).
Claude Cowork Guide
250Complete guide for non-coders using Claude Desktop with 29 business workflows (FR+EN) & 70 prompts
ccboard
96Real-time TUI/Web dashboard for Claude Code monitoring
Find your Adoption Path
Browse articles and guides by the Start, Build, or Scale decision you are working through now.
What I Write About
I write long-form articles about making AI-assisted development work in production, not just in demos, using real numbers from real codebases.
New to Claude Code? Start with Where to Start with Claude Code, the onboarding message I have sent on Slack more than 20 times. Then go deeper with Claude Code Under the Hood to understand the 8 tools and the 200K-token context window you are working with.
The Context Engineering series is the backbone of this blog and spans six parts on team systems, portability, and tooling. It opens with The Same Model, Opposite Results (+67% vs -19% on the same stack, with context as the variable).
The Real Cost of AI series covers what coding agents cost once retries, review, caching and quotas are counted, in nine parts from a $214 bill to measuring your own usage.
Production evidence
- AI Velocity Is Bidirectional covers 7 months of data showing debt accumulating as fast as features ship.
- From Afterthought to Infrastructure tracks 506 commits of AI config on a real codebase.
- Non-Technical to Production in 10 Days follows a non-developer modifying 80 files in production with Cursor.
- UVAL is the protocol I built to stop accepting code I don't understand.
Read my career background for the longer story of a VP Engineering building solo with AI agents.
Latest Posts
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.
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.
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.