Boris Cherny, the creator of Anthropic's Claude Code, says roughly 90% of the company's engineers now operate dozens or even hundreds of coding agents in parallel, a practice he attributes to a technique he calls "graph engineering." The remarks, drawn from a wide-ranging interview of nearly 40 minutes, offer an unusually concrete glimpse into how one of the leading AI labs is restructuring its own software work around fleets of autonomous agents rather than single, one-off prompts.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.