Tag

RAG

Date Topic Title
Engineering Moving DriveIQ's Search from Qdrant to Cloudflare Vectorize

DriveIQ's assistant lost its manuals the day its Qdrant cluster went idle. Here's how its search moved to Cloudflare Vectorize without changing a single answer. With receipts.

Engineering Ask Badge: How I Planned, Built and Locked Down a Chatbot That Only Knows One Website

How the Ask Badge chat on getoutwi.com works: the plan, the corpus, a Cloudflare Worker with Vectorize, GitHub-driven re-indexing, five locks, and a badger.

Engineering Get Out & Wisconsin: 124 Parks, a Chatbot, and a Badger Who Knocks on the Glass

Inside getoutwi.com: a crawler that rebuilds itself every Monday, maps with live DNR closures, an AI that only answers from the site, and Badge.

AI & ML RAG vs Fine-Tuning: A Decision Framework for Production

Fine-tuning and RAG solve different problems. Conflating them leads to expensive mistakes. Here's how to choose the right approach for your actual requirements.

AI & ML Stop Stuffing Your LLM Context: The Lost in the Middle Problem

More context does not mean better answers. LLMs deprioritize information in the middle of long prompts — and most RAG implementations get this wrong by default.

AI & ML Building an AI Blog Writer: From Topic to Published Post with n8n, Claude, and GitHub

How I built an AI agent that researches my 216 blog posts, generates complete drafts with validated frontmatter, and commits directly to GitHub. Paste a topic, get a production-ready post. The first of five components in an autonomous blog publishing system.

AI & ML RAG Chatbot Build Guide: From Plan to Production

How we turned 212+ blog posts into a searchable AI knowledge base with n8n, Qdrant Cloud, Voyage AI, and Claude. The vision, the reality, what broke, and where it's going. Includes architecture diagrams, problem-solving walkthroughs, and the exact technical components that make it work.

AI & ML Building a RAG Chatbot for My Blog with n8n, Qdrant Cloud, and Claude

How I turned 212 blog posts into a searchable AI assistant using n8n workflows, Voyage AI embeddings, Qdrant Cloud vector search, and Anthropic Claude — and what I learned about the messy reality of building RAG systems.

AI & ML Cortex Online School: Autonomous Learning from YouTube

How Cortex continuously learns from YouTube channels, validates improvements with RAG, and autonomously implements safe infrastructure changes with automatic rollback.

AI & ML How Cortex Built Itself: A Meta-Programming Journey Through Construction HQ Phases 4-8

A technical deep-dive into autonomous AI agents building production infrastructure in parallel. In 90 minutes, 7 parallel agents built 27,000+ lines of production-ready code implementing knowledge bases, K8s integration, governance, and self-healing capabilities.

AI & ML Building RAG Systems with Vector Databases

A comprehensive guide to building production-ready Retrieval-Augmented Generation (RAG) systems using vector databases, semantic search, and LLM integration patterns.