Steve Blank Your Startup Is Probably Dead On Arrival Your Startup Is Probably Dead On Arrival If you started a company more than two years ago, it’s likely that many of your assumptions are no longer true. You need to stop coding, building, recruitin…

Steve Blank's latest piece is a wake-up call: if your company is more than two years old, the world has shifted under your feet, and most of your founding assumptions probably aren't true anymore.

steveblank.com/2026/03/17/y...

I finally managed to implement an MCP App, i.e. an interactive widget that renders inside a conversation in ChatGPT, Claude, or any other MCP-compliant agent.

marmelab.com/atomic-crm/d...

Git AI - Track AI Code all the way to production Cross-agent observability from prompt to production. Track AI-generated code from Cursor, Claude Code, GitHub Copilot, Gemini, and more through the entire SDLC.

How much of your project code was written by #AI? Whether to track coding agent adoption in engineering teams or security risks introduced by vibe coding, it's time to track what Claude/Cursor/Copilot/Codex do.

usegitai.com

Supply Chain Attack on Axios Pulls Malicious Dependency from... A supply chain attack on Axios introduced a malicious dependency, plain-crypto-js@4.2.1, published minutes earlier and absent from the project’s GitHu...

The axios npm package, widely used for data fetching, has been compromised. Pin your version now. #NodeJS #Security socket.dev/blog/axios-n...

UX Quest - Train Your Usability Skills Spot the UX flaw! Examine mini-apps with deliberate usability problems, describe what's wrong, and get scored by an AI model.

AI is getting better at coding every day. Time to diversify your skills.

UX sense is hard to automate, easy to neglect.

We built a free browser game to train it: spot the usability flaw in mini-apps, describe it, get scored by ML.

#UX #OpenSource #AI

marmelab.com/ux-quest/

Software Will Never Die AI agents can now rewrite an app in hours. But software value lies in judgment, trust, and specification — not code. Here's why the craft of software engineering is evolving, not dying.

"Who needs devs now that agents can do the job" reminds me of "who needs banks now that we have the blockchain".

Same confusion. It was never about the technology. It's about trust.

marmelab.com/blog/2026/03...

Next time you need to build a single-page application, instead of letting your coding agent accumulate debt like crazy, point it to a well-tested and maintained open-source framework like ours!

Release v1.5.0 · marmelab/shadcn-admin-kit v1.5.0 (Feb. 2026) 🚀 Features Add <TextArrayInput> component for handling arrays of text values. Add <DateTimeInput> component for date and time input support. Add <ImageField> component for displ...

We've just releaased Shadcn Admin Kit version 1.5 with tons of new features, improvements and bug fixes. #OpenSource #React github.com/marmelab/sha...

If you’re a developer, I predict that you’ll soon build less web and mobile apps and much, much more MCP Apps. Fortunately, you can continue using the language you know and love, as this standard uses the iframe as the universal UI building block.

This is a turning point: AI assistants can now become true platforms, as they are no longer limited to text only. The assistant response is a canvas where apps can draw the UI elements necessary to perform a task.

MCP Apps - Bringing UI Capabilities To MCP Clients Today, we’re announcing that MCP Apps are now live as an official MCP extension. Tools can now return interactive UI components that render directly in the conversation: dashboards, forms, visualizati...

Generative UIs are becoming a reality: both ChatGPT and Claude now support MCP Apps, a new standard that allows tools to render tables, charts, and interactive UI widgets.

#GenerativeUI #AI #MCPApps

blog.modelcontextprotocol.io/posts/2026-0...

A Free Laravel Admin With API Platform and React-Admin Replace Laravel Nova with a flexible admin built on open standards and open-source tools.

Laravel admins often mean Nova. It works well. But it’s paid.

There’s a free alternative.

#Laravel + #APIPlatform + #ReactAdmin = a powerful admin UI on top of your Eloquent models.

JSX instead of PHP, but more flexibility and UI power.

marmelab.com/blog/2026/01...

Agent Experience Best Practices for Coding Agent Productivity Why do coding agents shine in some projects and fail in others? This article explains how to design your codebase so agents work autonomously and effectively.

Why do coding agents work great in some projects but fail badly in others?

In my experience, the difference is rarely the agent. It’s the codebase.

Here are 40+ best practices to make coding agents faster, safer, and more productive on real-world codebases.

marmelab.com/blog/2026/01...

L'évaluation des IAs : la recette secrète des agents pas trop bêtes - François Zaninotto - Forum PHP YouTube video by AFUP PHP

🛠️ Vous développez un agent IA ? Le prototype n’est que le début. Optimiser le coût, la rapidité et la pertinence représente 90 % du temps.

Découvrez comment les outils d’évaluation peuvent simplifier ce processus dans le dernier talk de @francoisz.bsky.social!👇 @afup.org

youtu.be/NjrbQ8aWDv8?...

Transactions and RLS in Supabase Edge Functions Edge functions are a powerful way to run server-side code close to your users. But how to handle transactions and Row Level Security (RLS) in these functions?

When using a backend-as-a-service like Supabase, you can only access the database through an HTTP API. Yet it is still possible to group queries into a transaction, without compromising on security. Read on to learn more. #database #security #NodeJS #supabase
marmelab.com/blog/2025/12...

MCP Apps: Extending servers with interactive user interfaces Today we’re introducing the proposal for the MCP Apps Extension (SEP-1865) to standardize support for interactive user interfaces in the Model Context Protocol. This extension addresses one of the…

Generative UI is about letting agentic apps create user interfaces on the fly.

A new specification called MCP Apps emerges, backed by Anthropic & OpenAI, to standardize it.It's very early stage ; to get an idea of the potential, try the popular MCP UI.
blog.modelcontextprotocol.io/posts/2025-1...

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?

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...

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 Learning Loop and LLMs How continuous learning shapes effective software development with LLMs

"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...

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 +…

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-...

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.

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...

Time flies #Symfony

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.

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/...

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.

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...

Scrum Is Done. Finished. History. We're going to need dual-track business agility.

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...

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

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…

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...

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?

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...

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…

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...