Muskan Tolani@TolaniMuskan

Review2Action AI is an AI-powered commerce intelligence platform designed to help businesses turn customer feedback and historical sales data into meaningful decisions. E-commerce businesses receive large volumes of reviews, making it difficult to identify recurring problems, understand customer sentiment, and determine which improvements should be prioritized. At the same time, poor demand planning can lead to stockouts or excess inventory. Our solution combines two modules. Review2Action AI allows users to upload customer review CSV files, analyze sentiment and recurring topics, explore analytics, and receive actionable business recommendations. SmartStock AI allows users to upload historical sales data, forecast demand over a selected time horizon, and support inventory replenishment planning. The platform integrates AMD Token Factory with the Qwen3.8-Flash-Next language model for supported AI-generated recommendations and explanations. Deterministic analysis and forecasting logic complement the language model, helping the system turn structured data into useful business insights. Built with React, TypeScript, Node.js, and Express, the prototype demonstrates how customer feedback intelligence and demand forecasting can work together in a single application. Our goal is to help commerce businesses make more informed decisions by connecting what customers say with what businesses need to plan.

🌎 Hybrid Hackathon | 💻 Online Build: 12-17 October 2026 | On-site phase: 17-18 October 2026 To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. The AMD Developer Hackathon: ACT III is a hands-on event for developers, founders, engineers and builders who want to push what’s possible with AI on real infrastructure. 📍 If approved for the on-site experience, you'll also have the opportunity to showcase your project live. Travel and accommodation will not be covered.