I built a set of agentic workflows to see how far coding agents can take routine automation. I wanted to answer a practical question: when should you use a coding agent like Claude Code to generate Python workflows, and when should you stick with visual workflow tools such as n8n? I tested real examples, deployed … Read more

Overview I built a full-featured Agentic RAG application that lets an LLM interact with private company data safely, efficiently, and transparently. The stack is intentionally simple: a React frontend, a Python FastAPI backend, and Supabase for storage, vectors, and auth. I used DocLing for document parsing and LangSmith for observability. The result is a multi-user … Read more

I created an automation that turns short lived AI calls into long running, reliable agents. These agents can research, synthesize, and produce reports that span hours and many data sources. The trick was adding a control layer, which I call an agent harness, around the AI so it can plan, persist progress, and resume work … Read more

I built an automation that lets AI agents answer questions about structured data without hallucinating. It uses natural language query, not just vector stores. The result is a database agent that learns useful SQL patterns over time and reuses them when similar questions come up again. Why vector stores alone often fail for tabular data … Read more

I built AI agents for businesses and quickly learned that vector search is powerful but not a cure-all. Vector search shines for conceptual, fuzzy queries. It struggles when answers require exact matches, structured calculations, or chaining facts across systems. Over hundreds of projects I helped with, the same blind spots showed up again and again. … Read more

I built an automation that fixes the single biggest weakness in most retrieval-augmented generation systems. The problem is simple: agents retrieve isolated fragments of documents, but they have no idea where those fragments sit in the document structure. That missing structure strips away the meaning those fragments need. I call the solution context expansion. It … Read more

Why agents need a map of your data I build AI agents all the time. They are great at language and reasoning. What they often lack is context about how pieces of data relate to each other. An agent can answer questions about a single record. It struggles when the answer depends on connections across … Read more

I built and tested many Retrieval-Augmented Generation (RAG) systems over hundreds of hours. What I learned is simple: there is no single best way to build RAG. The right design depends on what you need your system to do, how fast it must respond, how much accuracy you require, and what resources you can afford. … Read more

I spent two days building and testing Gemini File Search inside an n8n workflow. Lots of people called it a game changer that will kill traditional RAG systems. After hands-on work I found five critical aspects most people are missing. Some can quietly break a production system if you assume everything is taken care of … Read more

I created a video that walks through how I built a dynamic hybrid RAG (Retrieval-Augmented Generation) search engine in n8n, and this article captures that same approach in detail. My goal here is to explain why vectors alone often fail, how different retrieval methods work, and how you can combine them so an AI agent … Read more