Anthropic engineer Boris Cherny says his coding setup now involves “a few thousand” AI agents working for him overnight.
Loading audio narration…
Cherny, the creator of Claude Code, described his AI workflow during an interview with Sequoia Capital on May 4.
His answers — including how he mostly runs the agents via his phone — highlighted how some Silicon Valley engineers are beginning to use AI systems less like chatbots and more like always-on autonomous assistants.
“I have the Claude app, and if you open the Claude App, on the left-hand side, there’s this little code tab, and I just have a bunch of sessions going,” he said while showing his phone to the audience.
When asked how many sessions he had, Cherny said he typically runs “five to 10 sessions,” each containing multiple agents.
“Usually, every night, I have like a few thousand that are doing kind of deeper work,” he added.
Cherny said he relies heavily on two Claude Code features built for persistent automation: /loops and Routines.
He said users can schedule /loops locally via cron, while Routines run recurring tasks on a server, allowing engineers to keep agents working after their laptops are closed.
“It’s just like, the coolest thing,” he said. “If you haven’t experimented with it, highly recommend it.”
This isn’t the first time Cherny has shared how he uses his agents. In January, he shared his agentic setup on X, calling it “surprisingly vanilla.”
That five-month-old post has been saved over 104,000 times and has 8.1 million views as of publishing.
“It’s funny,” Cherny said during the interview. “I didn’t realize that it would be surprising for anyone. That was just like the way that I coded.”
Anthropic didn’t respond to a request for comment from Business Insider.
