Will Model Labs Eat the Agent Harness?
Harrison Chase says the agent harness should stay neutral, so the memory and context an agent builds are not locked to one model lab. A neutral harness holds state that accumulates before the agent runs and while it runs, including short-term and long-term memory. Some of the learning that makes an agent better over time lands in the model weights. A lot of it stays outside the model, in that context. If the context is tied to one model provider, you cannot switch when a better model appears, and you cannot leave if that provider raises rates.
The harness can be tied to one model or kept neutral. Right now the context is tied to the harness, and the harness connects the model to data, APIs, and memory. If memory is stored in a way that only one model knows how to use, the business is stuck. The point of a neutral harness is an open, controllable agent: change the model, change the harness, and change the context. Model labs train harnesses for what they see most, which is often coding. Sales, research, and law sit outside that, and those jobs need a harness the builder controls.
