A ground-truth benchmark for AI brand recommendations, built from Amazon's ESCI dataset where human raters labelled which brands are relevant to each query. Ranking brands by share …
A benchmark and dashboard that checks whether AI brand recommendations are correct, not just present, using Amazon's ESCI relevance judgements as ground truth.
How to automate routine software access provisioning while keeping human review where it matters. The central design decision is that the language model never makes the access …
Why AI visibility tools that query a model API don't measure what customers actually see in a chat app. A controlled experiment across seven brands found that turning search off …
Open-source tool that measures how brands show up across ChatGPT, Claude, Perplexity, and Gemini, reporting share of voice, sentiment, and cited sources.
Compares an LLM against a traditional ML pipeline on customer-review sentiment, benchmarking accuracy, auditability, and handling of sarcasm.
AI IT self-service portal on AWS and Claude that auto-approves or escalates software-access requests by policy, with a natural-language chat interface.