Why Do Domain Experts Win With Vertical Agents?
Harrison Chase says a founder should start a vertical agent at the harness layer, doing context engineering before any post-training of the model, because domain experts who can verify the work capture the value.
People say agent value sits in verification, whether the agent did the job well, because verification unlocks the next step, automation. The winners are the domain experts who can quantify what the value means, which is very hard. Building evals is a very hard job, so a lot of the value will accrue to whoever can write the verifiers and capture the domain knowledge. Vertical agents for different domains follow from that, because the domain experts best suited to write the verifiers or build the evals will be able to build harnesses and models. It will not be the harness alone or the model alone. It will be some combination of them.
The practical path is to start at the harness layer, do context engineering, tweak the harness, and once users are on board, start tweaking the model in post-training. Starting at the context or harness layer first brings a much higher return. The verticals will quantify what good looks like in a domain-specific way, and that lets them build vertical agents and vertical agent experiences. Different agents might have different experiences.
