Bring your AI agents to Basecamp

REWORK host Kimberly Rhodes speaks with 37signals co-founder and CTO David Heinemeier Hansson about Basecamp's command-line interface for external agents. Hansson frames CLIs and skills as an accessibility layer that makes existing product capabilities faster and more direct for agents than visual browser control.

Key Points Covered

• Browser success was still too slow: Agents could navigate Basecamp visually, but the interaction latency motivated a direct command-line interface [00:02:09]-[00:05:56].
• Tools turn prose into shared work: A launch request becomes to-dos, comments, messages, assignments, and schedule items inside a Basecamp project [00:05:56]-[00:07:37].
• Feedback loops matter: As with coding agents, terminal tools let an agent act, inspect errors, adjust the call, and continue [00:08:25]-[00:09:28].
• Accessibility can precede embedded AI: Hansson recommends exposing a product through CLIs and skills rather than adding native AI features that do not yet improve the workflow [00:10:23]-[00:14:05].
• Agents can build their own on-ramp: He reports that agents produced much of the Basecamp CLI and says the approach will extend to HEY and Fizzy [00:15:04]-[00:17:02].

The episode does not detail authentication, permission scoping, auditability, recovery, or comparative evaluation, so the demonstrated convenience is not a complete production-safety case.

Full video: https://www.youtube.com/watch?v=oE1Y_6W4Mj8(opens in a new tab)