I recently came across a new type of role advertised in career postings, the one of an "AI Product Builder": a seasoned individual who works as a hybrid between a product manager and developer. The premise is founded on the advancement of code harnesses and the desire to reduce the idea -> ship cycle. By having a single person own the requirements, and the implementation, that person is able to iterate and experiment faster.
Is this really possible in mid-2026 and can a conventional product manager evolve into such a role? As always the answer is that it depends.
Certainly code harnesses have contributed a lot to making agents more focused and reliable. The recent advancements have been in the following areas:
better prompt management (especially in the platform owners tools, e.g. Claude and Codex, that have the best knowledge on how to properly steer their models)
context management. That's where a lot of the investment went. For a given task, what is the minimum but sufficient amount of information that needs to be in context. This includes:
