MCP for Cloud & DevOps Engineers: What Model Context Protocol Actually Does
If you work in cloud or DevOps, you've probably seen "MCP" show up everywhere this year and quietly...
Tutorials
Follow-Up: Decision-Token Measurement, Format-as-Fallback, and What Changed
Thanks to Dipankar Sarkar, Mike Czerwinski, Max Quimby, and Ponsubash Raj R for the detailed comments...
How to Build an AI Agent Pipeline That Won't Delete Your Database
A practical guide to production AI agent safety: sandboxed execution, human-in-the-loop gates, idempotent actions, and rollback strategies.
Claude Code Burns 33K Tokens Before It Even Reads Your Prompt
A wire-level teardown of Claude Code vs OpenCode found a 4.7x token tax before your prompt is even parsed. Here's the actual byte-for-byte breakdown — and why it matters more than ...
How to Debug a Failing Test with AI (Step-by-Step)
How to Debug a Failing Test with AI (Step-by-Step) A test is red. The error message is...
Stop Hooks as Hard Constraints: Enforcing Claude Code Behavior Outside the Model
Prompt instructions are soft constraints that RLHF-trained deference and hedging can override under pressure. Claude Code stop hooks run after generation and before you see the out...
I Rebuilt My Courses on the Science of Learning (2026)
How I reworked 109 interactive lessons with 5 desirable difficulties (active recall, spaced repetition, the generation effect) and AI agents, all tested in production.
Publishing an ai-catalog.json for agentic discovery
Google and a Linux Foundation working group published Agentic Resource Discovery in 2026, an open...
From AI Chatbots to AI Operators: Why Travel Doesn't Need Another Assistant
Most AI tools in travel can answer questions. Very few can actually do the work. A delayed flight. A...
GhostCommit: the exploit your AI code reviewer can't see
A new attack technique called GhostCommit just made AI-assisted code review look like a liability....
Three Strangers on the Internet Just Made My Research Better — Here's What They Taught Me
Three Strangers on the Internet Just Made My Research Better — Here\'s What They Taught...
Claude Supervisor: wait out Claude Code usage limits, then auto-resume
If you use Claude Code for long, agentic tasks, you know the moment: you're mid-refactor, the agent...
I found the one AI coding skill that refuses to lie to you about its numbers
I wasn't looking for this. I was digging through Claude Code skill repos at 1am, the way you do, and...
How we designed the NeuroOffice AI agent architecture
NeuroOffice is a suite of AI agents built into Y-tech Bank’s business layer. Here’s the architecture...
enabling AI's Full Potential: Bridging the Gap from Sandbox to Production
Discover how OTF's innovative approach with CLAUDE.md and .cursorrules provides the structured context AI agents need to smoothly extend your codebase from de
Token Economics: Why Your AI Bill Is a Capital Decision, Not a Cost to Cut
Your Copilot and Cursor seats are approved. Adoption is climbing, engineers are shipping, the...
How I Built a Domain - Specific LLM for Public Transit - From Data Collection to Deployment
A complete walkthrough of building UmarTransit-1B, a 1.5B parameter model fine-tuned on real GTFS data from 15 transit agencies across 10 countries. Open source, runs on CPU, cost ...
Testing an AI API from a country where the official card checkout keeps failing
Disclosure and availability: DaoXE is a multi-model, multi-protocol API gateway we operate (OpenAI...
When to outsource web scraping vs build in-house (2026 framework)
Most articles about the build-vs-buy decision for web scraping assume you are making it from scratch....
I Could Review It. I Couldn’t Write It.
...now, I pride myself on being good at my job, I'm fast at catching mistakes, I'm efficient at...
I had my AI review its own code, and it found 3 bugs it had just written
Do you trust the code your AI assistant just wrote for you? I did. More than I should have. Lately,...
I measured what Claude does to a long screenshot
A 3066x28800 screenshot reaches the model at 276x2600. Here is the math, and what to send instead.
Building a Minimal AI Meeting Assistant: From Idea to Open-Source Project
AI meeting assistants have become one of the most practical applications of modern AI. Tools can now...
Why Multi-Agent Architectures Beat Single-Agent Setups in Enterprise Deployments
When companies start deploying AI agents, the playbook is usually the same. Buy whatever model tops...