What Is Factory Engineering at Warp?

Zach Lloyd says factory engineering means replaying a company's real tasks across models and harnesses so the team can see cost against correctness, and the target is the upper left corner: lowest cost, highest correctness. Warp has its own harness and also lets a team benchmark against other harnesses, including Codex. The output looks like published SweBench or TerminalBench results, run on the company's own work.

On one task set, one model was 95% correct and cost six bucks on average, while another was 93% correct and cost two bucks. The models in the chart are slightly older because the field changes fast.

The scores feed a model routing strategy or a harness routing strategy written for the company's own workflows and code base. The shift leaves guessing behind and applies a real engineering mindset to coding agents, so a team can tell whether the company is deploying them in the right way. Warp is building the infrastructure for companies that have already been trying to build their own versions of the same setup.