This is an incredible way to drive work. At 37signals we've always loved the way Basecamp allows you to "work in the open" where everything is visible to your coworkers. It makes it easy to see what someone is up to, spot when they might be stuck, and chime in with a novel idea. But it's not just about collaboration, every decision, all the discussion, and every image from sketch to final review are kept for posterity. Now, we're able to bring the same transparency to working with agents. It's all in Basecamp for the benefit of the team instead of lost inside everyone's Claude session.
Oh and did I mention it's fun?!
For example, you can chat about a feature idea, mention the agent, and it'll kick off a project, add some to-dos and start working. Super powerful and all in Basecamp's familiar tools. I'm loving this.
Who knew that 22 years ago when we launched Basecamp we'd have built the absolute best framework to work with humans and agents in the same place.
Here's @bitsweat talking to Clawdito (an agent) in Basecamp, assigning it work, getting responses, asking it to follow up, creating PRs, the whole thing.
And here's @jasonzimdars working with Marie (an agent) and JZ bot (another agent, his agent) in a comment thread on a message board. Can do this anywhere in Basecamp... on a to-do, card, file, document, photo, anywhere you can talk to humans async or real time, you can talk with your agents the same way. And they can respond the same way humans do, right in line, right where you'd expect, with all the context in the thread.
We've been running and refining this in our account for a while now. Anyone can do this today using the CLI. But we're also making it easier for people to create agent-users within Basecamp. Stay tuned for a lot more on this front.
Oct 2, 2026 · 1:05 AM UTC
5
3
46
20,900
