“Are you assessing its skills and its capability on a monthly or routine basis? How are you evaluating them, just like you would your human workforce, with standard check-ins”

“All agents are written .md files… these skills are like mini agents… they read the instructions, understand who you are, how you communicate… then AI uses the skill automatically”

“Most of the metrics is happening now on a monthly basis... insights... on a quarterly basis... I’m trying to refresh that possibly twice a year, possibly once a year”

“I’m typically pricing cash flows… the pricing exercise has been very similar… higher component of underwriting and qualitative assessment.”

“Authority comes down essentially to what decisions am I choosing as the human in the loop to make? What decisions am I giving to the agent to make? And what decisions can the AI agent never make?”