How do I tell when users are frustrated with my agent?
Frustration shows up in language before it shows up in churn: re-phrasing the same request, negative sentiment, repeated corrections, giving up mid-task. Flowlines detects this as the user_frustration signal on every session and rolls it up per user, so sustained frustration becomes a leading churn indicator instead of a postmortem.
By the time frustration reaches a survey or a cancellation, it's too late to act. But it's visible much earlier in the conversation itself: the user rephrases, repeats, corrects the agent, escalates tone, or abandons the session.
Flowlines scores these patterns as the user_frustration signal and stacks them per user over time. One frustrated session is noise. Three in a row from the same user, or a rising frustration rate across a cohort, is a signal you can route on.
Because frustration is tracked at the user and cohort level, you see not just “this session went badly” but “these users are trending toward at-risk”, early enough to intervene.
Last updated 2026-05-28