Retail

This is the final post in the series. The first three covered what I built and how. This one covers what I learned, what I’d do differently, and why this architecture matters beyond the demo. What worked Archetype-based catalog generation scaled cleanly. Writing 1180 product descriptions by hand would have been infeasible. Generating them one-by-one with Claude would have been slow and inconsistent. The archetype system with variation logic produced realistic, diverse products at scale with no manual writing and consistent quality across the catalog. ...

The previous posts focused on search. This one turns to the AI assistant — a floating chat widget that answers product questions, recommends complementary gear, and builds camping loadouts on request. Under the hood, it is a multi-turn conversation system with history, context injection when viewing a product, and dynamic retrieval when the query requires cross-product knowledge. What the assistant does ...

The previous post covered the architecture and indexing pipeline. This one is about the core value proposition: why semantic search matters and how to demonstrate it. The approach: build both keyword and AI search, run the same queries through each, and document where keyword search fails. The results make the case for semantic search more effectively than any architectural explanation could. What keyword search actually does Postgres full-text search works by tokenizing text into lexemes (normalized words), removing stop words, and matching query tokens against indexed documents. It’s fast, deterministic, and has been reliable for decades. ...

I built Ozark Ridge, a mock outdoor gear retail site with AI-powered product search and a Rufus-style product assistant. The project exists to demonstrate RAG (Retrieval-Augmented Generation) in a realistic e-commerce context. This is the first post in a series documenting the build. This one covers the architecture, the data and indexing pipeline, and the stack decisions behind the whole system. Later posts cover keyword vs semantic search, the AI assistant, and lessons learned. ...

Not every automation has to be sophisticated to matter. This one is a form, an AI analysis step, and a spreadsheet output. It runs on about ~1,500 products a month. Each run saves about 10 minutes of manual work. That adds up to ~250 hours per month and an estimated ~$500,000 per year in labor cost that no longer exists. This is a post about how it works, what made it possible, and what the experience taught me about where AI automation actually pays off. ...