Benoît Prioux
@binout.bsky.social
Enthusiast Software Developer 💚 @avec_alan 📣 Alan Recrute https://jobs.ashbyhq.com/alan?departmentId=8ba0fb44-ec79-4731-bf45-d65a821e24f0
Bonne nuit @devoxx.fr blog.zwindler.fr/2026/04/22/d...
DevoxxFR 2026 - Récap du mercredi (jour 1)
Les résumés des 3 jours de DevoxxFR 2026\nDevoxxFR - Récap du mercredi (jour 1) TODO DevoxxFR - Récap du jeudi (jour 2) TODO DevoxxFR - Récap du vendredi (jour 3) Premier jour de DevoxxFR 2026 C’est r...
blog.zwindler.fr
For years, every claims feature at Alan meant building it twice. A year ago, we broke that cycle. Here's what that journey looked like — from expensive first steps to compounding returns, and AI's role in it all 👇. medium.com/alan/univers...
Universalisation at Alan: How We Stopped Building Everything Twice
From duplicate codebases to shared flows: how we turned multi-platform pain into compounding gains.
medium.com
Part 3 of our document processing series is out — how we scaled our pipeline from French insurance docs to three countries and multiple use cases, without rewriting everything. This wraps up the series. Thanks for following along! buff.ly/9cQL4F3
Dans ce second et dernier article sur l'anti-bégaiement, je parle solutions : Anti-bégaiement : 3 stratégies pratiques d’idempotence. medium.com/@tpierrain/a...
Anti-bégaiement : 3 stratégies pratiques d’idempotence
TL;DR: Dans un précédent article, je vous parlais du bégaiement mal géré par beaucoup trop d’APIs et de pourquoi les agents IA allaient…
medium.com
La malédiction du happy path frappe encore, et même chez les géants de la tech (ici chez Microsoft) 😅 (on est mal avec tous ces agents dans la nature) 👉 Avec nos APIs qui bégaient là… aussi ! medium.com/@tpierrain/n...
Nos APIs qui bégaient, là aussi…
Nos APIs qui bégaient, là aussi… TL;DR: Nos APIs n’ont jamais été très bonnes pour gérer les retries (le fameux “bégaiement”). Tant que les appelants étaient des humains, ça passait …
medium.com
We think we built the best Python caching library in the world! RAM+Redis, atomic writes, distributed invalidation, async refresh, warmup, observability... Dive into this 5-part series, packed with diagrams, code snippets, dashboards, and numbers! medium.com/alan/alan-ca...
Few-shot examples are only as good as their labels. Ours were hallucinating values from memory. The LLM learned to do the same. Part 2 of the doc processing series: curated datasets, backtesting every change and separating parsing from human knowledge medium.com/alan/lessons...
Lessons from Running an LLM Document Processing Pipeline in Production
We evolved from text-only to multimodal, built curated reference datasets for RAG and developed an evaluation framework
medium.com
Ever wondered how Alan reimburses health claims so fast? Spoiler: we automated 70% of document processing. We just dropped the first article of our document processing series — stay tuned for more on how we're scaling this across other countries and use cases. buff.ly/2Lu7aWD
How we reached 70% document processing automation at Alan
We replaced our classic ML pipeline with a unified LLM-based approach using Markdown Transcription and few-shot RAG extraction
medium.com
« the data showed that the proportion of participants reporting negative developer experience nearly doubled over six months, rising from 14% to 27%, even as productivity held steady. » annievella.com/posts/the-mi...
The Middle Loop - Annie Vella
Early in my career, I took a job as a software developer at a large consultancy. Turns out the work mostly involved fixing other people’s Access databases by right-clicking and hitting “repair”. I las...
annievella.com
📣 We’re doing something a bit different at @alan: an on-site Engineering Recruitment Day! 🗣️ Meet the team 👨💻 Technical and fit stages in 1 day 🚀 Clear checkpoint and quick next steps 📍 Paris (Alan HQ) 🗓️ Tue, March 17 ⏳ Apply by Wed, March 11 👉 jobs.ashbyhq.com/alan/a8b3fe4...
Loïc Kervran et moi avons l'immense honneur de pouvoir parler à @devoxx.fr cette année 🥳 Nous vous présenterons "All-In sur la plateforme : nouveau Poker @Betclic" ♦️♠️♥️♣️ Un retour d'XP sur les challenges derrière la création (en un an 🤯 ) d'une Poker room à la croissance toujours plus forte 💪
Nouvel article qui capture l'évolution de mon usage du multi-tasking AI sur ces 4 derniers mois www.linkedin.com/posts/freder...
L'IA au quotidien - Paralléliser ses tâches agentiques | Frédéric Camblor
Nouvel article sur ma pratique de l'IA : aujourd'hui il est question de la manière dont je parallélise mes tâches. J'y aborde : - la fin de mon flux de production monothread - mon utilisation des wor...
linkedin.com
Devs who write about their work/company; talk at conferences - lots of companies in the past used to not care much about this and not value it the least. Feels like the tide is changing: people who do this but are not valued get hunted down by companies who understand this value
In a month I'll leave Doctolib. Not yet sure of what I will do next, if you have an interesting project do not hesitate to contact me www.linkedin.com/posts/aherit...
#opentowork #staffengineer #devx #ai #platformengineering | Arnaud Héritier
Open to New Challenges: Staff/Principal Engineer in AI-Assisted Dev, Platform Engineering, or DevX After 3.5 years at Doctolib, I’m ready for my next hands-on technical role. With my teams, we tackle...
linkedin.com
The engineer-manager pendulum model no longer accurately reflects how engineering leadership operates. Most of us aren’t just an IC or a manager. Technology has forced us to live somewhere in the middle. I wrote about what this actually looks like now: www.modernleader.is/p/pendulum-r...
The engineer–manager pendulum is breaking
The hybrid era of engineering leadership is here, and the traditional IC/manager model is no longer suitable.
modernleader.is
Le Call for Papers (CFP) pour Devoxx France 2026 est ouvert ! 🙌 ⏰ Clôture : 11 janvier 2026 à 23h59 (CET) 👉 Soumettez votre talk sur devoxxfr2026.cfp.dev Nous avons hâte de découvrir vos idées 💡
"Claude did it almost on its own while I was boiling water for my tea" That's how our engineers now fix flaky tests at Alan. Read more about our journey from manual debugging to AI-powered investigation in our latest article 👇 medium.com/alan/from-gu...
From Gut Feeling to AI assisted: How We Automated Flaky Test Investigation
Over the last year, we’ve improved our flaky tests investigation process, moving from manual debugging to an AI first solution. This…
medium.com
A big page has turned for me, I've left Red Hat. emmanuelbernard.com/blog/2025/11...
Leaving Red Hat - a 20-years page has been turned
After 20 years of an Open Source led career at JBoss and Red Hat, I have decided to leave this family and explore a new path. My journey at JBoss and Red Hat This is a long and not an easy page to...
emmanuelbernard.com
Je crois qu'une des choses les plus utiles que j'ai acquises au fil des années dans ma carrière de développeur c'est de faire une distinction nette entre une préférence et une conviction. C'est absolument indispensable pour travailler en équipe et trouver des compromis.
🧠 My @bdxio.bsky.social talk, Rewriting the Role: Developers in the Age of LLMs, is now a blog series. Part I is live: Programmers Are Always Doomed… Until They’re Not. From Fortran to Copilot, every era said “dev is dead.” But we’re still here. 👉 lostinbrittany.dev/en/programmers-are-always-doomed
« Récrire le rôle du développeur dans l’ère des LLMs » - réflexions très intéressantes sur l’évolution notre métier au vu de notre histoire 👏 @lostinbrittany.bsky.social #bdxio
There are many LLM benchmarks such as MMLU and GSM8k, but they're useless for AI agents. Real agents need to handle database state, tool calling, and multi-turn conversations. Stateful benchmarks show the path forward. New post on agent evaluation 👇
Benchmarking AI Agents: The Challenge of Real-World Evaluation
AI agents need stateful benchmarks. Unlike LLMs, agents interact with databases and users. We explore why and how to evaluate them…
medium.com
La couverture est officielle 😍 (enfin, j'ai pas de nouvelles, mais j'imagine, vu qu'on peut la voir sur tous les sites 😂) #50NuancesDeKubernetes
Le pouvoir sous-exploité de la similarité (dans le logiciel) medium.com/@tpierrain/l...
Le pouvoir de la similarité
TLDR; De tous les principes phares qui m’ont été utiles en tant qu’ingénieur logiciel, le pouvoir de la similarité est sans doute un des…
medium.com
Hop un petit article qui montre comment booster Claude Code avec différents serveurs MCP touilleur-express.fr
Le Touilleur Express | Blog sur le métier de développeur et la vie de freelance par Nicolas Martignole
touilleur-express.fr
Interesting article about Claude Code and why it is the "universal computer interface": steipete.me/posts/2025/c...
Claude Code is My Computer | Peter Steinberger
I run Claude Code with --dangerously-skip-permissions flag, giving it full system access. Let me show you a new way of approaching computers.
steipete.me