I Dug Through 300 Agent Failure Logs. The Problem Was Never the Prompt.
An open-source context engineering skillset just crossed 10k GitHub stars. After applying it to my own agent stack, I finally understand why agents fail.
← Back Get in touch
Blog
Simple thoughts on building, designing, and shipping.
⌘K
frouter: I Built a CLI That Finds Free AI APIs So You Can Vibe Code for $0
I couldn't sleep after a conversation about shipping more work publicly, so I built frouter at 3am. It pings free AI models in real-time and wires them into your coding tools with one keystroke.
7-Step Pipeline to Verify Code Written by AI Agents
When agents push 3,000 commits a day, humans can't review them all. Here's how to build a machine-verified pipeline that catches what people can't.
My Agent Called a Failed API 5 Times—The Bug Wasn't in the Code
When an agent repeats the same failing API call, code review won't help. Traces are the new source code for debugging AI agents.
I Was Too Lazy to Write CLAUDE.md — Turns Out That Was the Right Call
New benchmark data shows AGENTS.md and CLAUDE.md context files actually hurt coding agent performance. Sometimes laziness is the best engineering decision.
If the AI Bulls Are Right, the S&P 500 Crashes 38%
Citrini Research's 2028 macro scenario makes a chilling case: the more AI succeeds, the worse the economy gets. An analysis of Ghost GDP, the Intelligence Displacement Spiral, and why optimism itself may be the risk.
4 Updates from Anthropic, OpenAI, and Google: The Hidden Pattern
Three companies updated their coding agents at the same time. The directions overlap. The real battleground isn't models; it's how fast they absorb developer workflows.
5 AI Predictions for 2026: Agents, Chips, and Historic Exits
From the SaaSpocalypse to model-specific silicon, five bold predictions for where AI is heading in 2026, with roughly 50% confidence of getting them right.
The Cache Design That Cuts Claude Code API Costs by 90%
My API costs jumped 10x when the cache broke in production. The same day, Anthropic engineers explained exactly why.
Paste Your Prompt Twice and Watch Accuracy Change
Google Research validated it across 7 models and 7 benchmarks. No training, no prompt engineering. Just copy-paste. I tested it and here's what actually happened.
Get In Touch
Have a project in mind or just want to chat?
I'd love to hear from you.
I'm always open to a conversation.