June 10, 2025

The Human in the Machine: Why RAG Needs a 'Record and Refine' Workflow

In our last post, we perfected the search query. Now, we tackle a harder problem: teaching an AI to use it. This is the story of why our fully autonomous agent failed, and how we built a ‘Record and Refine’ workflow to make it truly powerful.

June 9, 2025

Crafting the Perfect Query: The Universal Translator for RAG

Building on our last discussion about RAG retrieval, this article tackles the query itself. We explore why a ‘one-size-fits-all’ boolean query fails and present a universal fallback strategy that ensures your AI can reliably search anywhere.

June 7, 2025

The 'R' in RAG: Why Web Search is the Hardest Part of AI

Discover the complexities of web search for RAG systems. This article explores common pitfalls, such as handling responsive design and e-commerce redirects, and provides robust solutions for reliable data retrieval.

June 5, 2025

Veridian.ai – AI-Powered Search for Modern Websites

Veridian.ai enhances website search with AI-powered capabilities, requiring no backend changes. Features include natural language understanding, smart product comparisons, and structured result displays.

June 2, 2025

The Conversational Commerce Revolution

Explore how AI-powered conversations are revolutionizing e-commerce, from the evolution of web interaction to practical implementation strategies for SMBs. Learn about the transition from static pages to intelligent conversational interfaces.

May 19, 2025

Optimizing LLMs for Edge Devices: A GCP & Hugging Face Tutorial

This tutorial offers a detailed workflow for optimizing Large Language Models (LLMs) for edge devices using Google Cloud Platform (GCP) and Hugging Face. It covers setting up a GCP environment, fine-tuning a small LLM, and then applying advanced optimization techniques including knowledge distillation, quantization (dynamic and static), and pruning. The guide also details how to export the final model to formats like ONNX and TFLite for deployment in browsers (with Transformers.js or ONNX Runtime Web) and on mobile devices.

May 18, 2025

Minimal Python Setup for LLM Development on MacBook

This guide provides a minimalist approach to setting up a Python development environment on a MacBook for LLM projects. It advocates for using pyenv and venv over Conda for a lightweight and flexible setup, and walks through the steps of installing Python, managing virtual environments, and handling dependencies with requirements.txt.

April 30, 2025

Inception

AI Strategy & Engineering Consultant with 20+ years of experience at Apple, Meta, and as a startup founder. Specializing in helping small businesses implement AI solutions, from strategy to deployment, with a focus on practical, scalable results.