“Purpose-built agents, not random AI functionalities, but really purpose-built agents that have certain guardrails and evals to make sure that the results that they are delivering are also reliable and also repeatable”

“One of the hottest companies coming out of Y Combinator is AI agent evaluation… to simulate all of those conversations, those edge cases, put them through and ensure consistency.”

“I think we've seen a pattern of employees being evaluated on AI usage… tracking usage of tools is the absolute wrong way of going about evaluating output.”

“First, document… second, turn a recurring process into a skill… third, once the skill works reliably, schedule it or connect it with other skills to create an agent”

“We're going to have agents that are actually monitoring other agents. And those agents are monitoring other agents are going to be very responsible for ensuring aligning that the current agents align to the task”