RAG Chatbot

GolfRules AI Chatbot

Personal Project

A retrieval-augmented generation (RAG) chatbot that solves the core problem with AI assistants: hallucination. By retrieving actual rule text before generating responses, every answer is grounded in the official rulebook with verifiable citations.

n8n workflow RAG Anthropic AI Postgres Memory Supabase vector DB

How It Works

User submits natural language query

Semantic search retrieves relevant rule chunks from vector database

Retrieved context injected into prompt with grounding instructions

LLM generates response constrained to retrieved context

Response includes rule citation for user verification

GolfRules AI RAG workflow diagram showing the n8n workflow with user query, vector database retrieval, context injection, and LLM response generation

Product Decisions

Component	Technology	Product Rationale
Vector DB	Supabase (pgvector)	Semantic search surfaces relevant rules even with imprecise queries
Generation	Claude (Anthropic)	Strong instruction-following ensures responses stay grounded in context
Memory	Postgres	Conversation persistence enables follow-up questions without re-explaining
Orchestration	n8n	Visual pipeline simplifies debugging; modular design allows component swaps

Why RAG over fine-tuning: Knowledge updates without retraining, citations enable user verification, and constrained generation eliminates hallucination risk.

What I Learned

💡 Without explicit instructions to say "I don't know," the model confidently makes up answers when the retrieved context doesn't have what it needs. Telling it when to admit uncertainty was key.
💡 For AI products where accuracy matters, users need to verify answers themselves. Citing the exact rule builds trust in a way that "the AI said so" never will.