Daniel Walsh

I created an automation that lets powerful cloud language models answer questions about private company documents without ever seeing real sensitive data. The cloud model only ever receives surrogate values. Real names, passport numbers, financials and other secrets stay inside my network. This article explains how I put that together, the challenges I ran into, … Read more

Agent skills have become one of the most useful design patterns for building practical AI agents. I created an automation that combines agent skills with code execution sandboxes inside a custom Python and React agent. The result is an agent that can not only answer questions but follow step-by-step workflows, execute code safely, and produce … Read more

I created an automation that dramatically reduces unnecessary LLM context and lets the model orchestrate complex workflows with real code. The two design patterns at play are simple in concept but powerful in practice: tool search and programmatic tool calling. Both solve problems that crop up as agents grow: tool definitions bloating the context window, … Read more

I created an automation that treats a knowledge base more like a living file system than a static set of vectors. Instead of relying only on semantic search, this approach lets an AI agent actually explore folders and files, form hypotheses about where answers live, and then dig deeper—just like a developer reading a codebase. … 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 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