It's late 2024, a few days after I launched the first version of Claude Code (then called Claude CLI) to team dogfooding. I walked into the office and saw my coworker Robert with a terminal up on his computer, Claude CLI running and a red/green diff view on screen.
I was surprised. This was back in the Sonnet 3.5 days, before the model was good at agentic coding. I had just given it a FileEdit tool the day before. Claude CLI was a prototype that I thought it wasn't useful for anything yet. But Robert was already starting to use it to write code & use git for him. I was still using the CLI as a note taker mostly, but I also started making it my go-to tool for using git as a result.
Jan 13, 2026 · 3:53 AM UTC
A couple months later, many engineers & researchers at Anthropic were using Claude daily. There was one day I remember walking into the office and saw a Claude Code terminal up on our data scientist's computer monitor! I asked if he was trying out Claude Code, and was shocked to learn that he was using it to do his work, to write and run SQL queries for an analysis, and to make little ascii plots in the terminal and using matplotlib.
We built Claude Code for engineers, and here was a data scientist using it to do his work too. The next week, the entire row of data scientists had Claude Code up on their screens.
Over the next few months, this happened over and over. First our designer started using Claude Code for prototypes and content fixes, then our finance person used it to build models and do financial forecasting, Sales used it to analyze data from Salesforce and bigquery, our user researcher used it to crunch survey results.
Fast forward to today, and people are using Claude Code to control their oven, recover wedding photos from a busted hard drive, analyze their DNA and medical records, haggle with customer support.
At some point all of this stopped being surprising. It became obvious that we should make it easier for people that want to use the Claude agent for things that are not coding. That's why we launched Claude Cowork today.
I felt sentimental about this launch because it reminded me of the early Claude Code days: the product is early, it doesn't work perfectly yet, but already people are finding it extremely useful for all sorts of things that are not obvious and also not coding. I can't wait to see how people use Cowork, and how the product evolves.
If you have any feedback as you use Cowork -- bugs, ideas, stuff we should build next -- tag me or @felixrieseberg
nitter.cf/bcherny/status/2010809…
Since we launched Claude Code, we saw people using it for all sorts of non-coding work: doing vacation research, building slide decks, cleaning up your email, cancelling subscriptions, recovering wedding photos from a hard drive, monitoring plant growth, controlling your oven.
These use cases are diverse and surprising -- the reason is that the underlying Claude Agent is the best agent, and Opus 4.5 is the best model.
Today, we're so excited to introduce Cowork, our first step towards making Claude Code work for all your non-coding work. The product is early and raw, similar to what Claude Code felt like when it first launched.
Cowork includes a number of novel UX and safety features that we think make the product really special: a built-in VM for isolation, out of the box support for browser automation, support for all your claude.ai data connectors, asking you for clarification when it's unsure, We are excited to see how you all use it.
Cowork is available now as a research preview for Claude Max subscribers in the macOS app. Click on “Cowork” in the sidebar: claude.com/download
the git workflow is still what makes it click for most people. was it actually landing clean diffs back then or did it need a lot of babysitting?
How do I bypass all the permissions on CLI? I have enough confidence and can allow CC to have all permissions on a folder?
please don't lose the developer focus. create a dedicated team that's only worried about software development use case.
I’m fan of Claude Code cli
But I discovered that Opus is not available with the Pro plan
Would be nice to have a limited allocation so that a user can plan a project with Opus, then execute it with Sonnet
I tried Code web, Claude os and iOS apps but the cli is still my fav
Recently I’m using Claude Code not only for coding but in more general ways. I really think Claude CLI ad my coworker. I can’t imagine lifebefore I started using Claude code. Best thanks to you and the team.
I really love this concept in the talk.
youtu.be/gv0WHhKelSE?si=xJIH…
its true it was good already on public release, even with opus 3.5
also, boris can you chime in on this question to your post:
nitter.cf/techguyver/status/2007…
seems like there a number of curious people about it
Q: Why do you teleport to web?
What's the advantage vs keeping using it on your terminal?
btw - I have a pretty similar setup to you except I use Tmux.
This allows me to have the tabs and have six agents per tab.
And I also date each session for easy retrieval in case I ever need to go back and continue.
for anyone seeing - i definitely recommend checking it out
