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)→
More from coding & agent
- Google's MCP Apps extension lets MCP servers return interactive UI components — rseroter · 2026-09-23
- Dev runs 32 coding agents burning 5-10B tokens a day in Zed — generativist · 2026-09-23
- Stanford paper: self-organizing agent team hits 66.7%, beats best single model's 48.8% — dair_ai · 2026-09-23
- Google's ToolGrad reverses tool-use data generation, hits 83.1 BFCL with 12B Gemma-3 — dl_weekly · 2026-09-23
- Using AI agents to book things still costs as much mental effort as doing it yourself — nabeelqu · 2026-09-23
- LangChain to unveil new products Thursday, previewed live at Interrupt keynote — LangChain · 2026-09-23