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 dashboard and benchmark that measures whether AI brand recommendations are correct, not just present, using Amazon's ESCI human relevance judgements as ground truth. Ranks brands …
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 appear in AI answer engines. Runs buyer-intent prompts across ChatGPT, Claude, Perplexity, and Gemini, then reports share of voice, …
Comparative sentiment analysis of customer reviews using a Generative AI (LLM-based) model vs. a traditional ML pipeline in RapidMiner. GenAI outperformed on sarcasm and …
AI-powered IT self-service portal built on AWS Bedrock and Claude. Auto-grants or escalates software access requests based on job-level policy. LLM chat interface lets employees …