Month: November 2025

Context Engineering: Why Building AI Agents Feels Like Programming on a VIC-20 Again TL;DR LLM context windows operate like virtual memory systems—paging information in and out based on task demands,…

Why AI projects are failing – explained Created on 2025-10-10 10:07 Published on 2025-10-10 10:15 TL;DR Only 5% of enterprises consistently extract AI value; 42% abandon most projects after POC…

Markdown as an Operating System Created on 2025-09-30 10:12 Published on 2025-10-04 02:30 Your operating system runs on binaries. Your AI agents should run on Markdown. Think about it: A…

Knowledge is a Tool: RAG for Agentic Systems Created on 2025-09-30 09:19 Published on 2025-10-03 03:30 Your AI agent just hallucinated. Again. You asked: “What’s our refund policy for enterprise…

AI as Interface: The Most Undervalued Role Created on 2025-10-02 07:01 Published on 2025-10-02 07:03 “It takes an advanced computer to be easy to use.” — Steve Jobs Steve Jobs…

MCP as the Tool Belt Standard: Giving AI Agents Hands and Eyes Created on 2025-10-02 05:01 Published on 2025-10-02 05:36 Your AI agent is a brain in a jar. It…

Observability for Agentic Systems: What to Log, How to Redact, How to Debug Created on 2025-09-30 08:31 Published on 2025-10-02 01:30 It’s 3am. Your AI agent just approved a $50,000…

Micro-Agents, Macro-Impact: Why Small, Composable AI Agents Beat One Mega-Brain Created on 2025-09-30 07:58 Published on 2025-10-01 01:00 Here’s the pattern killing most AI agent projects in 2025: one giant…

Think in Whole Stories: Why AI Coding Agents Write Better Code When They See the Complete Picture Created on 2025-09-30 06:08 Published on 2025-09-30 06:30 Here’s the pattern I keep…

Agentic Coding, Plain and Spicy Created on 2025-09-30 05:45 Published on 2025-09-30 05:50 Agents don’t hallucinate less. They loop better. The difference between a chatbot that writes code once and…