Most safety research is now done by agents: designing experiments, running evals, reading the results. Thornfield is building the harness that makes that work rigorous, reproducible and safe to run.
Researchers now direct agents that write the experiment code, run it across models, and summarize what they found. The bottleneck has moved from doing the work to trusting it.
General-purpose coding harnesses weren't built for this. They blur what an agent did with what it reported, lose the trail from result back to run, and give agents more access than safety work should allow. We think research agents need a harness that treats every action as evidence.
We're working closely with a small group of safety research teams while the harness takes shape. More to share soon.