From ReadWriteWeb to the agentic web
“Every AI agent needs a web browser,” said Paul Klein IV, CEO of headless browser vendor Browserbase, at this month’s AI Engineer World’s Fair. What is a headless browser? Simply put, it’s a web browser without a graphical user interface. Until very recently, they’ve been used primarily for running automated web app tests and for … Read more
The web browser has been the core app of the web for more than thirty years. Fundamentally, it hasn’t changed much over that time, but now it’s starting to be reimagined as an AI tool. Dia, a new web browser that invites you to “chat with your tabs,” has just been launched as an invite-only … Read more
This month marks the 30th anniversary of PHP being released to the world. To find out how PHP has evolved over the years, its technical improvements over the past decade, and the importance of PHP frameworks like Laravel and Symfony, I spoke to PHP core developer Derick Rethans. Rethans has been a PHP developer for … Read more
Believe it or not, it’s been over three years since Twitter announced it was being sold to Elon Musk. When that news broke, some Twitter users (myself included) began to move to the fediverse — a collection of decentralized web products powered by the W3C standard, ActivityPub. Many people thought this might be the beginning … Read more
When the web was first scaling up, content delivery networks (CDNs) became a way of dealing with the ever-increasing load. Akamai is widely considered the pioneer of CDN technology in the late-1990s, but arguably it’s been overtaken now by younger, more agile CDN competitors. At least that’s the view of Artur Bergman, co-founder and chief … Read more
Is RAG dead yet? That was the tongue-in-cheek question posed recently by Douwe Kiela, CEO of Contextual AI. And Kiela knows a thing or two about RAG (Retrieval-Augmented Generation) — he led the team at Meta that introduced the technique in a May 2020 research paper. Of course, Kiela’s post was a reaction to the … Read more
At today’s Google I/O, the general availability of Gemini Code Assist for individuals was announced. In the lead-up to the event, I spoke to Ryan J. Salva, a senior director of product management at Google Cloud, about this latest iteration of Gemini Code Assist, Google’s AI coding tool. In particular, we focused on the product’s … Read more
With all the hype around AI, it can be difficult to know which aspects of AI technology are actually being implemented inside enterprises. To find out, I spoke with Brian Wald, who heads up GitLab’s Field CTO team and is in regular contact with enterprise IT departments. Wald described the Field CTO role at GitLab … Read more
LONDON — With Kubernetes and the cloud native community now 10 years old, KubeCon was a chance to both look back and look ahead for Google’s Jago Macleod, engineering director of GKE and Kubernetes at the company. In a fascinating presentation at KubeCon + CloudNativeCon Europe in London this week, Macleod explained Google’s initial motivation … Read more
This week marks my 5th anniversary of working at The New Stack. When I started, in the final week of March 2020, I had to quickly get used to the “cloud native” world. What was Kubernetes and why did everyone keep talking about it, what did “serverless” mean exactly, what did the acronym CI/CD stand … Read more
With virtually every coding tool now infused with AI, developers are increasingly asking themselves: what type of coding tool should be my default now? Do I need one of those new-fangled “agentic IDEs” or is Visual Studio Code good enough? What role does the cloud play in AI tooling? To answer these questions, I’ve surveyed … Read more
Last November Anthropic launched the Model Context Protocol (MCP), an open source standard designed to streamline how AI models interact with APIs. As we explained earlier this month, the vision is to make MCP the universal method for AI agents to trigger external actions. MCP has drawn a lot of interest in its first few … Read more
Warp, the command-line terminal app built for AI, has finally arrived on Windows. Previously it was available only on macOS and Linux, but today’s launch significantly broadens its potential user base. I spoke with Warp’s founder and CEO, Zach Lloyd, about the news. We also discuss how Warp is positioning itself among the raft of … Read more
Google has just released a free version of Gemini Code Assist, its AI coding tool that up till now had primarily been available on paid business plans starting at $19 per month. Not only is Google opening up the tool to individuals for free, but it’s offering up to 180,000 code completions per month — … Read more
So far, 2025 has been the year of AI agents — where generative AI technology is used to automate actions. We’ve seen OpenAI’s Operator debut, demonstrating a prototype agent that can browse the web and do tasks for you. Now a new company called Orby is bringing that same approach to the enterprise, with a … Read more