Extension services are a keystone of information diffusion in agriculture. This paper exploits a large randomized controlled trial to track diffusion of a new technique in the classic Training and Visit (T&V) extension model, relative to a more direct training model. In both control and treatment communities, contact farmers (CFs) serve as points-of-contacts between agents and other farmers. The intervention (Treatment) aims to address two pitfalls of the T&V model: i) infrequent extension agent visits, and ii) poor quality information. Treatment CFs receive a direct, centralized training. Control communities are exposed to the classic T&V model. Information diffusion was tracked through two nodes: from agents to CFs, and from CFs to others. Directly training CFs leads to large gains in information diffusion and adoption, and CFs learn by doing. Diffusion to others is limited: other males adopt the technique perceived as labor saving, with an effect size of 75 percent.