causal

LLMs read every conversation to surface hidden issues

Companies historically sampled a small fraction of customer conversations with a team of about 20 people checking a rubric, but a language model can read every conversation, extract insights, flag the roughly 2% of conversations going badly, and draft suggested agent adjustments.

causalpending

Speaker

Jesse

Evidence Quote

“it'll literally just flag: hey, there's this 2% of conversations where things are not really going that well.”

Source

Jesse Zhang - Building Decagon - [Invest Like the Best, EP.443]— Invest Like the Best
Created: 11/17/2026, 9:59:28 AM

Your notes

Loading notes...