All Posts

By RJ Militante · June 2026 This is Part 2 of an ongoing series on AI memory management and context. Part 1: How I Use SSH and Claude Code to Run an AI Dev Lab From My Mac covers the remote development setup and how the file system becomes a persistent

This post is part of an ongoing series on AI memory and context management — how to give Claude persistent, structured knowledge of your projects across sessions, devices, and interfaces. This installment covers the foundation: SSH into a remote server, run Claude Code, and use plain markdown files to keep context

By RJ Militante · April 2026 I've been thinking of what my ideal Dev setup would be, an always-on resource that would allow me the most flexibility across situations, and arrived on setting up a VPS on DigitalOcean as a remote Dev server and AI Agents Lab. If you&

By RJ Militante · May 2026 This is part two of the shoppinglist-chat build. Part one covered rearchitecting the backend — moving off Azure, replacing local dependencies with hosted infrastructure, and fixing a hallucination bug caused by a RAG skip threshold that was too aggressive. By the end of that post, the

Rearchitecting a Shopping List Chatbot: Infrastructure, Bugs, and Lessons By RJ Militante · May 2026 Building an AI-powered shopping assistant sounds straightforward until you get into the details: which model, which vector database, how to handle embeddings, where chat history lives, how streaming works across a RAG pipeline. Each decision has

By RJ Militante · April 2026 The prompting fundamentals — role, context, command, format — apply everywhere. Claude.ai, ChatGPT, Gemini, all of it. What follows is specific to Claude Code, which changes the stakes considerably. The simplest way to explain Claude Code is this: Claude.ai and Claude Code use the same

AI Prompting: The Fundamentals By RJ Militante · April 2026 Most people are prompting AI with the equivalent of a text message. Two sentences. No context. And then they're frustrated when the output is generic. The core insight behind every technique in this post is this: the quality of

By RJ Militante · April 2026 Here are two prompts asking for the same thing. One of them will get you a usable result. One will get you something generic that needs three rounds of correction. Prompt A: Write a blog post about climate change and what businesses can do about