#harness

Recent work turns skills, harnesses, and context into objects you can search over and benchmark — optimizing the English around a frozen model instead of the model.

A new survey and Microsoft's BUILD 2026 release both landed on the same idea: agent capability is leaving the model and moving into the harness.

Six-hour agent runs are now real. The harness — checkpoints, durable state, recovery — matters more than the model. A field guide to the long-running pattern.