# Tessary frustration

Frustration is one of Tessary's built-in classifiers. It reads the user's messages and flags the
ones expressing annoyance, anger, or disappointment with the situation or the assistant.

It catches users having a bad time in ways that never show up in error rates: an agent that keeps
misunderstanding, loops, or makes the user repeat themselves. It runs over every trace at negligible
per-event cost. When it fires, the finding goes to triage, and findings ruled real issues become a
case, so a spike of frustrated users over one call site shows up as one investigable unit.

## Questions answered under this concept

- [Can the frustration classifier tell why a user is upset, or just that they are?](https://tessary.ai/answers/tessary-frustration/can-the-frustration-classifier-tell-why-a-user-is-upset)
- [Does a calm bug report count as frustration?](https://tessary.ai/answers/tessary-frustration/does-a-calm-bug-report-count-as-frustration)
- [Does one frustrated message trigger an alert?](https://tessary.ai/answers/tessary-frustration/does-one-frustrated-message-trigger-an-alert)
- [What is Tessary's frustration classifier?](https://tessary.ai/answers/tessary-frustration/what-is-tessarys-frustration-classifier)
- [Why do users who are having a bad time never file a ticket?](https://tessary.ai/answers/tessary-frustration/why-dont-frustrated-users-file-tickets)

---

Source: https://tessary.ai/answers/tessary-frustration
All concepts: https://tessary.ai/answers
From Tessary, agent reliability for AI agents in production: https://tessary.ai
