blogs-amoydutta.hashnode.devExplainable Recommendations in Practice: A Demo-Driven ApproachThis blog complements my earlier post on AI-based explainability (xAI) for recommendation systems and the corresponding Movie Recommendations App. While demo apps should ideally speak for themselves, explainable systems often benefit from guided cont...Feb 10·8 min read
blogs-amoydutta.hashnode.devThe End of the Black Box: Why the "Why" is the Future of PersonalizationIf you spend five minutes in a Product Management circle today, the word "Personalization" will likely be the most overused term in the room. We treat recommendation engines as the silent engines of growth, the invisible hands that guide users throug...Jan 26·8 min read
blogs-amoydutta.hashnode.devBuilding a Smarter Product Chatbot: What RAG Gets Right—and Where It BreaksImagine you're on a vast electronics e-commerce site like samsung.com. You're surrounded by hundreds of products across dozens of categories. You have specific needs- "a durable camera for hiking" or "a quiet laptop for a student" - but the website's...Dec 22, 2025·11 min read
blogs-amoydutta.hashnode.devBreaking Down RAG: Why Chunking Can Make or Break Your LLMTL;DR:Retrieval-Augmented Generation (RAG) helps large language models (LLMs) like GPT-5 and Claude 4.5 access private, real-time, or domain-specific data by retrieving relevant chunks before generating answers. This article breaks down what RAG is, ...Nov 4, 2025·7 min read
blogs-amoydutta.hashnode.devBuilding a Basic Product Inquiry Chatbot with an LLM — Part 3: Improving Context and Evaluating PerformanceWelcome back! In Part 2, you built a working product inquiry chatbot that could understand user queries, extract product information, and respond through a simple web interface. It worked — but it wasn’t perfect. It couldn't handle follow-up question...Oct 29, 2025·6 min read
