Anthropic brings Claude Code to the web | TechCrunch

Anthropic launched a web app on Monday for its viral AI coding assistant, Claude Code, which lets developers create and manage several AI coding agents from their browser.

Claude Code for web is now rolling out to subscribers to Anthropic’s $20-per-month Pro plan, as well as its $100- and $200-per-month Max plans. Pro and Max users can access Claude Code on the web by navigating to claude.ai (the same website for Anthropic’s consumer chatbot) and clicking into the “Code” tab, or through the Claude iOS app.

The launch marks Anthropic’s latest attempt to evolve Claude Code beyond a command-line interface (CLI) tool that developers access from a terminal. By putting Claude Code on the web, Anthropic hopes developers will spin up AI coding agents in more places.

It’s increasingly competitive for tech companies trying to make their AI coding tools stand out. While Microsoft’s GitHub Copilot once dominated the space, Cursor, Google, OpenAI, and Anthropic now have highly performant AI coding tools of their own — many of them already available on the web. That said, Claude Code is arguably one of the most popular. Anthropic’s flagship coding tool has grown 10x in users since its broader launch in May, and the product now accounts for more than $500 million of the company’s revenue on an annualized basis.

Anthropic product manager Cat Wu tells TechCrunch in an interview that she attributes a large part of Claude Code’s success to the company’s AI models, which have become a favorite among developers in recent years. However, Wu also says the Claude Code team deliberately tries to “sprinkle in some fun” to the product wherever they can.

Wu said that Anthropic will continue to put Claude Code in more places, but the terminal will likely remain the home base for their AI coding product.

“As we look forward, one of our key focuses is making sure the CLI product is the most intelligent and customizable way for you to use coding agents,” said Wu. “But we’re continuing to put Claude Code everywhere, helping it meet developers wherever they are. Web and mobile are a big step in this direction.”

Anthropic claims that 90% of the Claude Code product itself is written by the company’s AI models. Wu, who was previously an engineer, says that she rarely ever sits down at a keyboard to write code anymore, and mostly just reviews Claude Code’s outputs.

Early AI coding tools worked like an autocomplete tool, finishing lines of code as developers wrote them. But the agentic generation of AI coding tools — including Claude Code — allow developers to spin up agents that work autonomously. This shift has made millions of software engineers act more like managers of AI coding assistants in their day-to-day jobs.

The change has not been welcome to every developer. One recent study found that some engineers were actually slower when using AI coding tools like Cursor. Researchers suggested one factor could be that engineers in the study spent much of their time prompting and waiting for AI tools to finish, rather than working on other problems. AI coding tools also struggle in large, complex code bases, so engineers may have spent a lot of time working through incorrect responses from the AI model.

Nevertheless, companies like Anthropic are continuing to push ahead making AI coding agents. Anthropic CEO Dario Amodei predicted a few months ago that AI should soon write 90% of code for software engineers. While that may be true inside of Anthropic, the shift may taken longer to pan out in the broader economy.