# How TheFork uses Arize AI

As published on [arize.com](https://arize.com/customers/how-thefork-uses-evals-to-boost-conversions-with-arize-ax-on-aws/). Captured by usedby on 2026-10-05.

- Company: [TheFork](https://www.usedby.ai/companies/thefork.md)
- Tool: [Arize AI](https://www.usedby.ai/tools/arize-ai.md)
- Industry: [Travel & Hospitality](https://www.usedby.ai/companies/industry/travel-hospitality.md)
- Teams: AI engineering, Product, Customer Service

## What the story says

TheFork uses Arize AX to trace and evaluate its LLM-powered features, such as the Ask TheFork semantic restaurant search and customer service assistants. It monitors quality, latency and cost in production, runs online evals to catch regressions, and shares the results between product and engineering teams.

Summary written by usedby from the source page, in English. The figures are those of Arize AI and TheFork, not ours.

> Tracing exposed the duplicate work. TheFork removed it, eliminating unnecessary computation and materially reducing p95 latency for the flow.

> Thanks to visibility in Arize, we were able to intervene before an issue reached production.
>
> Amir Bitaraf, Senior Machine Learning Engineer

> 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.
>
> Luca Temperini, CTO

## What usedby checked

We compared the story with its live page on 2026-10-05.

- Checked: the passage quoted above is copied word for word from the page, near the name of TheFork.
- Checked: TheFork uses Arize AI. Confirmed line. Latest check across sources: 2026-10-05.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/thefork-arize-ai · How we check: https://www.usedby.ai/methodology