Stop Wasting LLM Budgets: High-Performance Semantic Caching with Spring AI and pgvector
Stop Wasting LLM Budgets: High-Performance Semantic Caching with Spring AI and...
Tutorials
Google Paid $2.7B to Keep Its Best AI Researcher. He Left Anyway.
In 2024, Google paid $2.7 billion to bring Noam Shazeer back. Shazeer invented the transformer...
Turing's Mirror — A Game About the Question We Still Haven't Answered
This is a submission for the June Solstice Game Jam What I Built Turing's Mirror is a...
I built a free AI-powered relocation tool comparing 95 countries and 668 cities — here's how I did it
The Problem I was researching international relocation and found the existing tools...
Motif Learning Protocol: Prompt Engineering for Knowledge That Actually Sticks
TL;DR Most AI learning prompts help you recognize ideas. This one trains recall — via a...
The Day I Realized AI Agents Need Circuit Breakers
When people talk about AI agents, the conversation usually revolves around reasoning, planning,...
The Aftermarket She Diagnosed is the Aftermarket She Prescribed
Jen Easterly correctly identified that cybersecurity is an aftermarket for software quality failures. Then she celebrated an AI that makes the aftermarket faster. The cure she name...
Evaluating Kimi 2.5 vs Kimi 2.6: What happens to agent skills when the model gets smarter?
When a stronger model ships, there are two questions every skill author should want answered, and...
Goal In, DAG Out: How Open-Multi-Agent Turns a Goal into a Task DAG
In most TypeScript agent frameworks you wire the task graph by hand. open-multi-agent's runTeam() hands a goal to a coordinator that builds the DAG for you — here's the mechanism, ...
AI Agent Blind Spot Detector: Find Failed Conversations Before They Become Churn
Build an AI agent blind spot detector with unresolved-intent clustering, outcome scoring, trace evidence, review queues, and product feedback loops.
Stop sleeping your agent loop for 5 minutes
Your agent's idle timer talks to the prompt cache, and most loops are written as if it does not. The five-minute nap is the worst number on the board. Here is why, and the timing h...
How I Built a Programmatic SEO Pipeline with n8n + Claude API (and deployed 200+ pages in 3 days)
A few months ago, a client asked me to rank on 150+ local search queries across 5 cities — with a...
The agent economy solved 'how to pay.' It still hasn't solved 'who to trust.'
PayPal's real innovation in 1999 wasn't moving money. Banks already moved money. What PayPal did was...
Kitana: Why I’m Replacing Token Prediction With Dictionary Traversal
What If Language Understanding Starts With a Dictionary Instead of a Model? LLM →...
"EcoSphere AI: Why I separated 'logic' from 'AI' when building a carbon footprint assistant"
The Trap Most Carbon Apps Fall Into When you say "build a carbon footprint app," the...
💻 The Forward-Deployed Engineer 🤖 Playbook 📖
A practical, straight-to-the-point field manual for the role The New Stack calls "AI's hottest job"...
From Prompting ChatGPT to Orchestrating AI Agents: Two Years as an Ordinary Engineer
Two years ago, my interaction with AI was mostly limited to asking ChatGPT questions and checking its...
What Is an Agent Loop? How AI Agents Reason, Act, and Iterate
A practical explainer on the agent loop, how it works, why it is different from a chatbot, and where human-in-the-loop controls fit in.
Why I'm building a place to practice catching AI's bugs
Two moments made me start building Loupe. Neither was some grand realization — they were just things...
Monitorear agentes de IA con CloudWatch
Las dos ideas que hicieron el trabajo: Los modos de falla ya son líneas de log. Conviértelos en...
The Hidden Layer Behind Every Smart AI App: RAG, MCP, and Agentic Systems
If you've spent any time with ChatGPT, Gemini, or Claude, you already know they're impressive. Ask...
NVIDIA SkillSpector: Should You Scan Your AI Agent Skills Before Installing Them?
If you have been using Claude Code, Codex CLI, Gemini CLI, or any agent framework that supports...
Turso: A Rust Rewrite of SQLite. Setup Guide and Whether It's Worth Your Time
If you have spent any time in the SQLite-adjacent corner of GitHub lately, you have probably seen the...
Your AI feels slow? Maybe it's not dumb—you're making it work one thing at a time
📖 Originally published on my blog. Part of a series on building with Claude Code. For a while I'd...