The use case: how TheFork deploys Arize AI
TheFork uses Arize AX to trace, evaluate and monitor its LLM-powered features such as Ask TheFork, a restaurant search experience. It applies LLM-as-a-judge and code-based evals, online evals on live traffic, drift alerts, and cost and latency tracking to catch regressions and find performance issues.
In the customer’s words
Arize AX on AWS gives us prompt-level tracing, automated evaluations, and drift alerts, so we catch regressions early and meet strict Service Level Objective (SLOs) at scale.Thanks to visibility in Arize, we were able to intervene before an issue reached production.Other AI tools used by TheFork
Other public relationships recorded on usedby.
Explore TheFork’s AI stackArize AI users in Travel & Hospitality
Companies in the same sector, with public evidence.
See all Arize AI customersGo straight to the source
Based on Arize AI’s published case study. We check the public evidence; the results are reported by the vendor.
arize.com- Last checked
- Nov 16, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of TheFork.
- TheFork uses Arize AIChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
TheFork cut p95 latency on a critical flow by finding and removing duplicated embedding calls. The team also caught regressions before users did, and could see what a quality gain cost in latency and spend before shipping.






