Unilever · Google Cloud
15-35% increase — retailer sales
Independently reportedOther · Other · Classical ML · Scaled
Other
CollegeVine · Refuel
Vendor-reportedEducationIn productionEnterpriseLLM
Vendor-reported. The customer is named and the numbers are quoted from the source page, but the account comes from the vendor. No independent confirmation.
Reported by refuel.ai (vendor self-report). Checked against the source page on 2026-09-05. 5 of 5 figures below appear on that page word for word.
The problem
CollegeVine needed to improve the output quality of their AI agents by detecting and fixing incorrect claims at scale, as existing models had hallucination risks and outdated data.
What was deployed
- Vendor
- Refuel
- Products
- Refuel Cloud, Refuel-LLM
- Models
- GPT-4o-mini, GPT-4o, Refuel-LLM
- Technique
- LLM
- Build or buy
- Bought and customised
- Deployment
- SaaS
- Data used
- human-verified, labeled data
- Scale
- 2B+ tokens per day
What changed
Each row is quoted from the source. Figures we could not find on the page in those words are marked — they are kept, not deleted, so you can judge them.
50% fewererrors
“CollegeVine’s custom built model with Refuel achieved 50% fewer errors”
Quoted word for word from the source · round percentage, no baseline given
40% fasterspeed
“40% faster speeds”
Quoted word for word from the source · round percentage, no baseline given
60% in cost reductionscost reductions
“60% in cost reductions compared to GPT-4o.”
Quoted word for word from the source · round percentage, no baseline given
93%accuracyfrom sub 85%
“fine-tuned Refuel-LLM to achieve 93% accuracy on a held-out dataset”
Quoted word for word from the source
< 2 daysengineering effort for deploymentfrom 3-4 weeks
“The end to end process required < 2 days of engineering effort, compared to 3-4 weeks of engineering needed for projects of a similar undertaking without Refuel.”
Quoted word for word from the source
“We are amazed at how easily we are able to deploy fine-tuned models that outperform GPT for classification tasks. We have hundreds of such use cases at CollegeVine and are excited to partner with the Refuel team as we scale our agent platform for higher ed in 2025.”
Sources
- refuel.ai — vendor self-report
Similar deployments
ANZ Bank · NVIDIA
0.82 — Gini coefficient for assessing risk
Independently reportedBanking & finance · Other · Classical ML · Pilot
BHP Billiton
zero — accidents due to driver drowsiness
Independently reportedOther · Other · Classical ML · In production · 2022
DSST: College View · Playlab, Class Companion, Manta AI
Vendor-reportedEducation · Other · NLP · In production · 2024
Cubo Ai · Google Cloud
more than 10X — user growth supported with same IT workforce
Vendor-reportedOther · Other · Computer vision · Scaled · 2019
Precision HVAC & Cooling · AutoScale My Biz
15+ — High-Value After-Hours Leads Captured
Vendor-reportedOther · Other · LLM · In production