15 years of shipping production systems and leading engineering teams. Real code, real metrics, and the tradeoffs behind every decision.
18 total posts
Learn how I built a deep research agent that fans out across sources, then refutes its own findings with three skeptics before reporting a single cited claim.
Learn why I moved agent orchestration into durable workflow steps instead of a coordinator agent, and the model, safety-gate, and cost tradeoffs it carried.
Protect your enterprise CMS stack against the vulnerabilities Mythos exposed with this platform-specific checklist for Sitecore, Umbraco, and Optimizely.
Map OS abstractions to Claude Managed Agents architecture and build a three-agent auto-PR pipeline that plans, codes, and reviews autonomously.
Discover how Claude Managed Agents replaces months of custom agent infrastructure with a decoupled architecture that cuts time-to-first-token 60%.
Explore Chrome's WebMCP protocol that lets websites expose structured tools to AI agents, replacing brittle scraping with stable, typed APIs.
Discover how 30KB of prompt engineering replaced a SQLite-backed codebase to become a complete plugin design system for Claude Code's 6 extension points.
Learn how I built a 29-tool MCP server that handles product analysis, GTM strategy, content generation, and launch tracking without leaving the terminal.
Explore how I built a 32-tool MCP server with health scanning, issue tracking, release management, and operational runbooks for Claude Code plugins.
Build portable AI agent capabilities with Claude Code's SKILL.md format. The Agent Skills open standard works across 10+ platforms including GitHub Copilot.
Explore Claude Skills' three-tier progressive disclosure architecture and learn to build advanced workflows using executable scripts and team deployment.
Explore how MCP Apps turn AI chat into an interactive canvas with embedded dashboards, forms, and 3D visualizations—no client-specific code required.