# Tessary cost drift

cost_drift is one of Tessary's built-in classifiers: a tripwire that watches each call site's spend
against its own past. It tracks dollars per turn, with token counts attached as evidence.

It catches the quiet ways an agent gets more expensive: a prompt that grew, retries that multiplied,
caching that stopped working. Comparisons run against the call site's own history, both its recent
normal and a reference pinned at the last deploy, so sudden jumps and slow creep both register. A
drop in cost shows up as clearly as a rise. Findings go to triage, where the ones ruled real issues
open cases.

## Questions answered under this concept

- [Can cost_drift catch a cost that creeps up slowly, not just a sudden spike?](https://tessary.ai/answers/tessary-cost-drift/can-cost-drift-catch-a-slow-cost-creep)
- [Does cost_drift work for a scheduled agent that has no user sessions?](https://tessary.ai/answers/tessary-cost-drift/does-cost-drift-work-for-a-scheduled-agent-with-no-sessions)
- [Is cost_drift turned on by default?](https://tessary.ai/answers/tessary-cost-drift/is-cost-drift-turned-on-by-default)
- [How do I tell traffic growth apart from a broken agent in my LLM bill?](https://tessary.ai/answers/tessary-cost-drift/tell-traffic-growth-from-a-broken-agent-in-the-bill)
- [What is Tessary's cost_drift classifier?](https://tessary.ai/answers/tessary-cost-drift/what-is-tessarys-cost-drift-classifier)
- [Why does each turn get pricier as an agent's run goes on?](https://tessary.ai/answers/tessary-cost-drift/why-does-each-turn-get-pricier-as-a-run-goes-on)

---

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