Pragmatic Frontier

Focus is the moat.

Pragmatic Frontier is a small applied AI lab. We run closed frontier models and open weights in one harness, and the evals decide which takes each step. The job is to spend test-time compute well on any long-horizon task: the thinking, tool calls and retries a model burns over hours of unattended work.

What we build

A domain-specific harness removes every step between an idea and its outcome: a person states the idea, and the harness delivers the outcome. Each research target, once met, applies to an enterprise workflow and gives the company full sovereignty: model, harness and data stay on machines it controls.

The harness picks the model per step, not per job. Each step goes to the cheapest model that passes its eval, and an open model takes over the day it passes.