The use case: how Rox deploys Snorkel AI
Rox builds an AI-powered sales platform with agents that write personalized outbound emails. It uses Snorkel's evaluation suite to score its LLM-as-a-judge against human experts, improve the judge's alignment, and use it to find and fix errors in its outbound email model before shipping.
More reported results
Figures published in Snorkel AI’s case study. They are not independently measured by usedby.
Using the Snorkel Evaluation Suite, Rox scored the judge against human experts and found it aligned only around 75% of the time.
The aligned judge surfaced an issue with the prototype outbound model, which used the wrong recipient name around 11% of time, enabling Rox to correct the model’s behavior.
In the customer’s words
Off-the-shelf models aren’t capable of delivering the quality we need to ensure our agents are accurately personalizing outbound emails.Other AI tools used by Rox
Other public relationships recorded on usedby.
Explore Rox’s AI stack
Other companies using Snorkel AI
Customers across industries, with public evidence.
Defense Innovation UnitConfirmed
ExperianConfirmed
Amazon Web ServicesObserved
AnthropicObserved
Brown UniversityObserved
GoogleObservedGo straight to the source
Based on Snorkel AI’s published case study. We check the public evidence; the results are reported by the vendor.
snorkel.ai- Source published
- May 29, 2025
- Last checked
- Oct 5, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 99%Checked
The figure is on the page; its label is our wording.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Rox.
- The publication dateChecked
Read from the page’s own metadata, never guessed.
- Rox uses Snorkel AIChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Achieved 99%+ accuracy with specialized evaluators enabling sufficient trust to ship a critical email outbound feature.