Search & retrieval

Consumer Reports · NineTwoThree

Vendor-reportedNonprofitPilotLLMLive 2024

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 ninetwothree.co (vendor self-report). Checked against the source page on 2026-09-06. 1 of 1 figures below appear on that page word for word.

The problem

Building a sophisticated RAG system that could understand user’s ambiguous queries and then elegantly find answers and relevant information from CR’s vast database of articles, ratings and reviews.

What was deployed

Vendor
NineTwoThree
Products
AskCR
Technique
LLM
Build or buy
Bought and customised
Deployment
Custom build
Data used
CR’s vast database of product recommendations, reviews and information, articles, ratings and reviews, structured ratings and reviews data
Timeline
7 months

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.

over 10X improvementguardrails performance

We were able to improve guardrails performance by over 10X and implemented a product retriever to allow the model to be able to answer more of CR’s products.

Quoted word for word from the source

Difficulties and limits

Sources

Similar deployments

Walmart · Microsoft

22% — global ecommerce growth

Independently reportedRetail & e-commerce · Search & retrieval · LLM · In production · 2024

Osprey · NOVOS

72.6% — share of AI answers

Vendor-reportedRetail & e-commerce · Search & retrieval · LLM · In production

Safe · Victoria Olsina

40.88% — Enterprise keyword visibility

Vendor-reportedOther · Search & retrieval · LLM · In production

SoWork · iGrow

100% — AI Visibility Score

Vendor-reportedTechnology & software · Search & retrieval · NLP · In production · 2026

WS Audiology · QueryNow

85% increase — daily active users

Vendor-reportedHealthcare · Search & retrieval · NLP · In production