François Zaninotto
@francoisz.bsky.social
CEO at @marmelab, founder of react-admin & GreenFrame. #sustainability #React #Leadership #Agile #NodeJs #WebPerf #UX #Security #OSS @francoisz @francoisz@fosstodon.org
Have you come across Spec-Driven Development yet?
One AI writes the specs, another writes the code.
Sounds smart, but it's basically waterfall in disguise.
Here’s why we should stay agile instead.
marmelab.com/blog/2025/11...
One AI writes the specs, another writes the code.
Sounds smart, but it's basically waterfall in disguise.
Here’s why we should stay agile instead.
marmelab.com/blog/2025/11...
Spec-Driven Development: The Waterfall Strikes Back
Kiro, Spec-kit, Bmad, Tessl, and other SDD frameworks turn business analysts into Markdown reviewers. Isn't there a more agile way to use Coding Agents?
marmelab.com
November 12, 2025 at 4:37 PM
Have you come across Spec-Driven Development yet?
One AI writes the specs, another writes the code.
Sounds smart, but it's basically waterfall in disguise.
Here’s why we should stay agile instead.
marmelab.com/blog/2025/11...
One AI writes the specs, another writes the code.
Sounds smart, but it's basically waterfall in disguise.
Here’s why we should stay agile instead.
marmelab.com/blog/2025/11...
Etsy's Web Performance team implemented the Speculation Rules API (SRA) to prefetch product listing pages from search results, resulting in significant performance gains (20-24% improvement in metrics like TTFB, FCP, and LCP). #WPO www.etsy.com/codeascraft/...
www.etsy.com
November 6, 2025 at 2:04 PM
Etsy's Web Performance team implemented the Speculation Rules API (SRA) to prefetch product listing pages from search results, resulting in significant performance gains (20-24% improvement in metrics like TTFB, FCP, and LCP). #WPO www.etsy.com/codeascraft/...
"The ability to phrase our intent in natural language and receive working code does not replace the deeper understanding that comes from learning each language's design, constraints, and trade-offs." This analysis of #CodingAgents on #SoftwareDevelopment Is spot on. martinfowler.com/articles/llm...
The Learning Loop and LLMs
How continuous learning shapes effective software development with LLMs
martinfowler.com
November 6, 2025 at 9:48 AM
"The ability to phrase our intent in natural language and receive working code does not replace the deeper understanding that comes from learning each language's design, constraints, and trade-offs." This analysis of #CodingAgents on #SoftwareDevelopment Is spot on. martinfowler.com/articles/llm...
Do #React Server Components Improve #Performance? When compared to a pure SPA, they reduce the LCP but don't suppress the initial interactivity gap. The main performance benefit comes from completely rewriting data fetching to be Server Components-first. www.developerway.com/posts/react-...
React Server Components: Do They Really Improve Performance?
A data-driven comparison of CSR, SSR, and RSC under the same app and test setup, focusing on initial-load performance and the impact of client- vs server-side data fetching (including Streaming +…
www.developerway.com
October 30, 2025 at 2:04 PM
Do #React Server Components Improve #Performance? When compared to a pure SPA, they reduce the LCP but don't suppress the initial interactivity gap. The main performance benefit comes from completely rewriting data fetching to be Server Components-first. www.developerway.com/posts/react-...
Using AI coding agents? You’re probably missing one thing: specs.
I built vibe-spec, a CLI that extracts requirements from your coding agent logs and generates functional specs automatically.
#AI #DevTools #OSS #softwareengineering
marmelab.com/blog/2025/10...
I built vibe-spec, a CLI that extracts requirements from your coding agent logs and generates functional specs automatically.
#AI #DevTools #OSS #softwareengineering
marmelab.com/blog/2025/10...
vibe-spec: Generate Specifications From Coding Agent Logs
AI coding assistants can build software in semi-autonomy, but without specifications, projects lack functional definitions. The solution? Extract problem statements directly from conversation logs.
marmelab.com
October 30, 2025 at 9:53 AM
Using AI coding agents? You’re probably missing one thing: specs.
I built vibe-spec, a CLI that extracts requirements from your coding agent logs and generates functional specs automatically.
#AI #DevTools #OSS #softwareengineering
marmelab.com/blog/2025/10...
I built vibe-spec, a CLI that extracts requirements from your coding agent logs and generates functional specs automatically.
#AI #DevTools #OSS #softwareengineering
marmelab.com/blog/2025/10...
Agentic Search surpasses Retrieval Augmented Generation (RAG): Teaching an agent to use grep is far more efficient than chunking, embedding and similarity search. #AI www.nicolasbustamante.com/p/the-rag-ob...
The RAG Obituary: Killed by Agents, Buried by Context Windows
Why Retrieval-Augmented Generation Won’t Survive the Context Revolution and the End of Chunking, Embeddings, and Rerankers as We Know Them.
www.nicolasbustamante.com
October 21, 2025 at 8:48 AM
Agentic Search surpasses Retrieval Augmented Generation (RAG): Teaching an agent to use grep is far more efficient than chunking, embedding and similarity search. #AI www.nicolasbustamante.com/p/the-rag-ob...
How to add metadata to 100M product descriptions? Etsy Engineering shares their journey with #LLMs, eval and monitoring. Great insights about a real-life #GenAI use case. www.etsy.com/codeascraft/...
www.etsy.com
October 20, 2025 at 8:48 AM
How to add metadata to 100M product descriptions? Etsy Engineering shares their journey with #LLMs, eval and monitoring. Great insights about a real-life #GenAI use case. www.etsy.com/codeascraft/...
Every developer hates AI hallucinations. But what if those “mistakes” are what make AI seem intelligent?
Neuroscience says: noise isn’t a bug — it’s the engine of adaptability.
#AIEngineering #AIAgents #LLMs #SoftwareArchitecture
marmelab.com/blog/2025/10...
Neuroscience says: noise isn’t a bug — it’s the engine of adaptability.
#AIEngineering #AIAgents #LLMs #SoftwareArchitecture
marmelab.com/blog/2025/10...
Why AI Agents Need to Make Mistakes
Developers often try to eliminate errors from AI agents. But science shows that being wrong — within reason — is what makes intelligence adaptive.
marmelab.com
October 20, 2025 at 8:29 AM
Every developer hates AI hallucinations. But what if those “mistakes” are what make AI seem intelligent?
Neuroscience says: noise isn’t a bug — it’s the engine of adaptability.
#AIEngineering #AIAgents #LLMs #SoftwareArchitecture
marmelab.com/blog/2025/10...
Neuroscience says: noise isn’t a bug — it’s the engine of adaptability.
#AIEngineering #AIAgents #LLMs #SoftwareArchitecture
marmelab.com/blog/2025/10...
Scrum was revolutionary for human teams—but AI doesn't need standups, sprints, or sticky notes.
The future of work requires dual-track agility: a slow lane optimized for human collaboration & meaning, and a fast lane for AI precision & speed.
#agile
substack.jurgenappelo.com/p/scrum-is-d...
The future of work requires dual-track agility: a slow lane optimized for human collaboration & meaning, and a fast lane for AI precision & speed.
#agile
substack.jurgenappelo.com/p/scrum-is-d...
Scrum Is Done. Finished. History.
We're going to need dual-track business agility.
substack.jurgenappelo.com
October 10, 2025 at 8:48 AM
Scrum was revolutionary for human teams—but AI doesn't need standups, sprints, or sticky notes.
The future of work requires dual-track agility: a slow lane optimized for human collaboration & meaning, and a fast lane for AI precision & speed.
#agile
substack.jurgenappelo.com/p/scrum-is-d...
The future of work requires dual-track agility: a slow lane optimized for human collaboration & meaning, and a fast lane for AI precision & speed.
#agile
substack.jurgenappelo.com/p/scrum-is-d...
Reposted by François Zaninotto
Demain, c’est le Forum PHP organisé par l’ @afup.org ! Et devinez quoi ?
@francoisz.bsky.social, CEO de marmelab, sera présent pour vous donner des conseils sur l'évaluation des agents IA ! 🤖
⏰ 12h40 à 13h00
📅 9 octobre 2025
📍 Disneyland Paris
🔗 event.afup.org
#ForumPHP #PHP #Symfony
@francoisz.bsky.social, CEO de marmelab, sera présent pour vous donner des conseils sur l'évaluation des agents IA ! 🤖
⏰ 12h40 à 13h00
📅 9 octobre 2025
📍 Disneyland Paris
🔗 event.afup.org
#ForumPHP #PHP #Symfony
October 8, 2025 at 1:02 PM
Demain, c’est le Forum PHP organisé par l’ @afup.org ! Et devinez quoi ?
@francoisz.bsky.social, CEO de marmelab, sera présent pour vous donner des conseils sur l'évaluation des agents IA ! 🤖
⏰ 12h40 à 13h00
📅 9 octobre 2025
📍 Disneyland Paris
🔗 event.afup.org
#ForumPHP #PHP #Symfony
@francoisz.bsky.social, CEO de marmelab, sera présent pour vous donner des conseils sur l'évaluation des agents IA ! 🤖
⏰ 12h40 à 13h00
📅 9 octobre 2025
📍 Disneyland Paris
🔗 event.afup.org
#ForumPHP #PHP #Symfony
MCP servers make LLM-powered agents super powerful, but also super vulnerable to all kinds of new attacks. The core vulnerability, prompt injection, is still way too easy to trigger. #Security #AI simonwillison.net/2025/Apr/9/m...
Model Context Protocol has prompt injection security problems
As more people start hacking around with implementations of MCP (the Model Context Protocol, a new standard for making tools available to LLM-powered systems) the security implications of tools built…
simonwillison.net
October 2, 2025 at 8:48 AM
MCP servers make LLM-powered agents super powerful, but also super vulnerable to all kinds of new attacks. The core vulnerability, prompt injection, is still way too easy to trigger. #Security #AI simonwillison.net/2025/Apr/9/m...
Is your frontend team making 10+ API calls per screen and waiting weeks for backend changes?
New article: When you need a Backend-for-Frontend (and when you don't) 🧵
Real examples from Netflix, SoundCloud + implementation strategies
marmelab.com/blog/2025/10...
New article: When you need a Backend-for-Frontend (and when you don't) 🧵
Real examples from Netflix, SoundCloud + implementation strategies
marmelab.com/blog/2025/10...
Do you need a Backend For Frontend?
When your frontend teams are drowning in API complexity and your backend team is overwhelmed with frontend-specific requests, the BFF pattern might be your lifeline. But is it always the right choice?
marmelab.com
October 1, 2025 at 10:02 AM
Is your frontend team making 10+ API calls per screen and waiting weeks for backend changes?
New article: When you need a Backend-for-Frontend (and when you don't) 🧵
Real examples from Netflix, SoundCloud + implementation strategies
marmelab.com/blog/2025/10...
New article: When you need a Backend-for-Frontend (and when you don't) 🧵
Real examples from Netflix, SoundCloud + implementation strategies
marmelab.com/blog/2025/10...
When teams produce code faster than they can understand it, it creates what I’ve been calling “comprehension debt”. [...] When we have to edit the code ourselves, this debt is the extra time it’s going to take us to understand it first. #AI #Coding codemanship.wordpress.com/2025/09/30/c...
Comprehension Debt: The Ticking Time Bomb of LLM-Generated Code
An effect that’s being more and more widely reported is the increase in time it’s taking developers to modify or fix code that was generated by Large Language Models. If you’ve wo…
codemanship.wordpress.com
October 1, 2025 at 8:48 AM
When teams produce code faster than they can understand it, it creates what I’ve been calling “comprehension debt”. [...] When we have to edit the code ourselves, this debt is the extra time it’s going to take us to understand it first. #AI #Coding codemanship.wordpress.com/2025/09/30/c...
Engineers at CloudKitchens are saving 3 hours weekly with #GenAI coding tools, with no decline in code quality. They measured it through careful benchmarks, not industry hype. #DX #DevEx techblog.cloudkitchens.com/p/study-and-...
Study and Update on GenAI DevEx
Internal GenAI developer tools, and learnings about vendors
techblog.cloudkitchens.com
September 25, 2025 at 8:48 AM
Engineers at CloudKitchens are saving 3 hours weekly with #GenAI coding tools, with no decline in code quality. They measured it through careful benchmarks, not industry hype. #DX #DevEx techblog.cloudkitchens.com/p/study-and-...
Reposted by François Zaninotto
⏰ Plus qu’un mois avant le #ForumPHP2025 !
Rejoignez-nous à Disneyland Paris pour célébrer non seulement les 30 ans de #PHP mais aussi les 25 ans de l' @afup.org, les 20 ans de @symfony.com & les 10 ans d' @api-platform.com ! 🎂
On a hâte de vous y retrouver !
🔗 event.afup.org
Rejoignez-nous à Disneyland Paris pour célébrer non seulement les 30 ans de #PHP mais aussi les 25 ans de l' @afup.org, les 20 ans de @symfony.com & les 10 ans d' @api-platform.com ! 🎂
On a hâte de vous y retrouver !
🔗 event.afup.org
September 9, 2025 at 9:53 AM
⏰ Plus qu’un mois avant le #ForumPHP2025 !
Rejoignez-nous à Disneyland Paris pour célébrer non seulement les 30 ans de #PHP mais aussi les 25 ans de l' @afup.org, les 20 ans de @symfony.com & les 10 ans d' @api-platform.com ! 🎂
On a hâte de vous y retrouver !
🔗 event.afup.org
Rejoignez-nous à Disneyland Paris pour célébrer non seulement les 30 ans de #PHP mais aussi les 25 ans de l' @afup.org, les 20 ans de @symfony.com & les 10 ans d' @api-platform.com ! 🎂
On a hâte de vous y retrouver !
🔗 event.afup.org
Will augmented coding lead to fewer or more programmers? Nobody knows, but some skills matter no matter the outcome: understanding, integration, and judgment. Inspiring thoughts by the great @kentbeck.com. #AI tidyfirst.substack.com/p/programmin...
Programming Deflation
When Code Gets Cheaper Every Day
tidyfirst.substack.com
September 23, 2025 at 1:03 PM
Will augmented coding lead to fewer or more programmers? Nobody knows, but some skills matter no matter the outcome: understanding, integration, and judgment. Inspiring thoughts by the great @kentbeck.com. #AI tidyfirst.substack.com/p/programmin...
Reposted by François Zaninotto
ARTE 🤝 Marmelab : Depuis 2016, nous avons la chance de collaborer avec ARTE pour développer des briques essentielles de la plateforme ARTE. tv.
Aujourd'hui, nous vous emmenons dans les coulisses de ce partenariat ! 😉👇
marmelab.com/blog/2025/09...
Aujourd'hui, nous vous emmenons dans les coulisses de ce partenariat ! 😉👇
marmelab.com/blog/2025/09...
ARTE x Marmelab : Dans les coulisses d’ARTE.tv
Interview croisée avec Agathe Michalski, Responsable Technique, et Virginie Rieber, Product Owner chez ARTE, sur la collaboration avec Marmelab.
marmelab.com
September 23, 2025 at 9:22 AM
ARTE 🤝 Marmelab : Depuis 2016, nous avons la chance de collaborer avec ARTE pour développer des briques essentielles de la plateforme ARTE. tv.
Aujourd'hui, nous vous emmenons dans les coulisses de ce partenariat ! 😉👇
marmelab.com/blog/2025/09...
Aujourd'hui, nous vous emmenons dans les coulisses de ce partenariat ! 😉👇
marmelab.com/blog/2025/09...
Reposted by François Zaninotto
📣 Big news: Atomic CRM just got a makeover!
It now uses @shadcn.com as part of its updated tech stack.
Why @shadcn.com?
✅ You own your code
✅ 100% customizable
✅ Semantic design tokens
👉 Perfect for modern React devs
🔗 Check out Atomic CRM’s new look:
marmelab.com/atomic-crm/
#React #OSS #shadcn
It now uses @shadcn.com as part of its updated tech stack.
Why @shadcn.com?
✅ You own your code
✅ 100% customizable
✅ Semantic design tokens
👉 Perfect for modern React devs
🔗 Check out Atomic CRM’s new look:
marmelab.com/atomic-crm/
#React #OSS #shadcn
September 19, 2025 at 2:23 PM
📣 Big news: Atomic CRM just got a makeover!
It now uses @shadcn.com as part of its updated tech stack.
Why @shadcn.com?
✅ You own your code
✅ 100% customizable
✅ Semantic design tokens
👉 Perfect for modern React devs
🔗 Check out Atomic CRM’s new look:
marmelab.com/atomic-crm/
#React #OSS #shadcn
It now uses @shadcn.com as part of its updated tech stack.
Why @shadcn.com?
✅ You own your code
✅ 100% customizable
✅ Semantic design tokens
👉 Perfect for modern React devs
🔗 Check out Atomic CRM’s new look:
marmelab.com/atomic-crm/
#React #OSS #shadcn
Friday rant: Ctrl+Q is way too close to Ctrl+S.
Nothing like trying to save your work and accidentally rage-quitting your entire IDE instead.
Who approved this keyboard layout? Show yourself. 😤
Nothing like trying to save your work and accidentally rage-quitting your entire IDE instead.
Who approved this keyboard layout? Show yourself. 😤
September 12, 2025 at 8:57 AM
Friday rant: Ctrl+Q is way too close to Ctrl+S.
Nothing like trying to save your work and accidentally rage-quitting your entire IDE instead.
Who approved this keyboard layout? Show yourself. 😤
Nothing like trying to save your work and accidentally rage-quitting your entire IDE instead.
Who approved this keyboard layout? Show yourself. 😤
Fascinating read about all the low-level programming techniques used by Bun to outperform (by an order of magnitude) every other #NodeJS package manager. I learned a lot! bun.com/blog/behind-...
Behind The Scenes of Bun Install
Learn how Bun is able to cut install times by up to 25×. Bun skips Node.js's overhead with direct system calls, cache-friendly data layouts, OS-level copy-on-write, and full-core parallelism.
bun.com
September 12, 2025 at 8:48 AM
Fascinating read about all the low-level programming techniques used by Bun to outperform (by an order of magnitude) every other #NodeJS package manager. I learned a lot! bun.com/blog/behind-...
Big O notation for beginners, with examples and diagrams. A good reminder of the basics of algorithmic complexity. samwho.dev/big-o/ samwho.dev/big-o/
Big O
A visual introduction to big O notation.
samwho.dev
September 9, 2025 at 1:05 PM
Big O notation for beginners, with examples and diagrams. A good reminder of the basics of algorithmic complexity. samwho.dev/big-o/ samwho.dev/big-o/
LLMs can write code, but building software requires more than that. #AI #Programming zed.dev/blog/why-llm...
Why LLMs Can't Really Build Software - Zed Blog
From the Zed Blog: Writing code is only one part of effective software engineering.
zed.dev
September 5, 2025 at 1:03 PM
LLMs can write code, but building software requires more than that. #AI #Programming zed.dev/blog/why-llm...
Are AI coding tools going to replace developers, or supercharge them?
In my opinion, AI-augmented assistants like Claude Code and Copilot Agent aren't a threat—they're an opportunity.
#AI #SoftwareDevelopment #Programming
marmelab.com/blog/2025/09...
In my opinion, AI-augmented assistants like Claude Code and Copilot Agent aren't a threat—they're an opportunity.
#AI #SoftwareDevelopment #Programming
marmelab.com/blog/2025/09...
The Bright Future Of Developers
A new breed of developers is emerging. They ship production code daily but can't write a for loop. They're not imposters – they're the future of programming.
marmelab.com
September 3, 2025 at 8:51 AM
Are AI coding tools going to replace developers, or supercharge them?
In my opinion, AI-augmented assistants like Claude Code and Copilot Agent aren't a threat—they're an opportunity.
#AI #SoftwareDevelopment #Programming
marmelab.com/blog/2025/09...
In my opinion, AI-augmented assistants like Claude Code and Copilot Agent aren't a threat—they're an opportunity.
#AI #SoftwareDevelopment #Programming
marmelab.com/blog/2025/09...