Loading…
RAG-powered medical Q&A assistant
MedQuery grounds every answer in a curated set of medical reference documents, reducing hallucination risk compared to a plain language-model chat.
Documents are chunked, embedded, and retrieved at query time, then passed to Llama 2 as context alongside the user's question.
Long medical documents produced retrieval chunks that lost important context when split naively.
Switched to overlapping, section-aware chunking that kept headings attached to their content, which noticeably improved retrieval relevance.
AI-powered sales coaching ecosystem
An end-to-end coaching platform that evaluates commercial calls, tracks sales activity, and answers rep questions from company documents.
After-sales service management platform
A platform covering claims, field interventions, stock, payments, and real-time messaging for after-sales service teams.
Smart library management app
A Flutter app for modern library management with OCR scanning, barcode lookup, translation, and an AI FAQ assistant.