<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Retail on Tyler Wells</title><link>https://www.tylerwells.dev/tags/retail/</link><description>Recent content in Retail on Tyler Wells</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 16 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.tylerwells.dev/tags/retail/index.xml" rel="self" type="application/rss+xml"/><item><title>Building Ozark Ridge: Lessons Learned and What I'd Do Differently</title><link>https://www.tylerwells.dev/posts/ozark-ridge-post-4-lessons-learned/</link><pubDate>Thu, 16 Apr 2026 00:00:00 +0000</pubDate><guid>https://www.tylerwells.dev/posts/ozark-ridge-post-4-lessons-learned/</guid><description>[Retail AI Series 4/4] What worked, what didn&amp;#39;t, what I&amp;#39;d do differently in v2, and why this project matters for e-commerce AI.</description></item><item><title>Building the AI Product Assistant: Context Injection, Multi-Turn Chat, and Cross-Product Retrieval</title><link>https://www.tylerwells.dev/posts/ozark-ridge-post-3-ai-assistant/</link><pubDate>Wed, 15 Apr 2026 00:00:00 +0000</pubDate><guid>https://www.tylerwells.dev/posts/ozark-ridge-post-3-ai-assistant/</guid><description>[Retail AI Series 3/4] How to build a Rufus-style AI assistant that answers product questions, suggests complementary gear, and builds camping loadouts — with conversation history, context injection, and dynamic retrieval.</description></item><item><title>Keyword Search vs Semantic Search: Why Natural Language Queries Need Vector Embeddings</title><link>https://www.tylerwells.dev/posts/ozark-ridge-post-2-keyword-vs-semantic/</link><pubDate>Tue, 14 Apr 2026 00:00:00 +0000</pubDate><guid>https://www.tylerwells.dev/posts/ozark-ridge-post-2-keyword-vs-semantic/</guid><description>[Retail AI Series 2/4] Side-by-side comparison of keyword and semantic search, why keyword search fails on natural language queries, and what the retrieval scores actually tell you.</description></item><item><title>Building AI Search for a Retail Website: The Stack and Why</title><link>https://www.tylerwells.dev/posts/ozark-ridge-post-1-stack/</link><pubDate>Sun, 12 Apr 2026 00:00:00 +0000</pubDate><guid>https://www.tylerwells.dev/posts/ozark-ridge-post-1-stack/</guid><description>[Retail AI Series 1/4] Building a mock outdoor retail site with AI-powered product search and a Rufus-style assistant. This post covers the architecture, stack decisions, the indexing pipeline, and why RAG matters for e-commerce.</description></item><item><title>How a Simple Power Automate Workflow Automated 250+ Hours of Work Per Month</title><link>https://www.tylerwells.dev/posts/retail-power-automate-workflow/</link><pubDate>Fri, 20 Feb 2026 00:00:00 +0000</pubDate><guid>https://www.tylerwells.dev/posts/retail-power-automate-workflow/</guid><description>Eliminate costs tied to repetitive corporate tasks with simple workflows like this -- a Microsoft Form + a Power Automate flow + an AI prompt</description></item></channel></rss>