The Self-Driving Company

Amjad Masad and Scott Kennedy on running Replit as what they call a self-driving company, meaning agents deployed across most functions rather than just engineering. Engineering agents write, review and test code and root-cause production incidents; a manager agent spawns others to coordinate work loops; and there are sales, data, support and marketing agents, plus one that analyses user feedback and validates its own improvements through A/B tests.

The numbers, all self-reported, cover early January to late June: lines of code up 5.8x, and 2.9x more code per engineer once you control for hiring, with the team roughly doubling. The quality metrics they put alongside that are flat rather than improved, which is the point they are making: code review latency flat, PR reversion rates flat, production incidents flat, mean time to mitigation falling. Agents now save about 30% of human PR review time, and escalated support tickets resolve 60% faster.

The framing they keep returning to is that nobody was automated away:

A self-driving company is not one without people. People still choose the destination.

Worth the standard discount for a CEO describing his own company with numbers only he can see, and lines of code is a soft measure of output. The more useful claim is the cheap one to test elsewhere: their internal agent ran at 10x lower cost than the vertical-specific tools it replaced while matching them.