Stop training agents on chat alone: product behavior data carries 10-100x more signal

techNmak · x · 2026-09-23

After interviewing CTOs, Chief AI Officers, and product heads deploying agents at scale, the author spots a pattern: everyone invests in learning from agent conversations, while 90% of the real signal — clicks, hesitation, page views, abandoned flows, conversions, churn — sits untouched right next to the chat window.

His argument: that behavioral surface is 10-100x richer than the conversation itself and is the context agents need to be genuinely useful in enterprises. He calls out CopilotKit as one of the few teams actually acting on this.

Related event: Product Behavior Signals Are 10-100x Richer Than Chat Logs(2 posts)→

Original post →

More from coding & agent

coding & agent channel →