AI Coding Agents in 2026: How MCP Is Changing Software Development
Learn how AI coding agents work in 2026, why MCP matters, and how GitHub Agent HQ and Xcode are changing modern software development.
welcome to my corner of the web →
Building full-stack platforms, AI systems, and security infrastructure — and writing about the craft behind it.
How I built Site 4 That — a SaaS platform with 40+ AI tools for ADHD, relationships, productivity, and parenting using Next.js 15, Claude, and Stripe.
Most CLAUDE.md files try to do too much. Here is a modular approach using conditional rules, subagents, and hooks that keeps context lean and Claude focused.
Learn how React SPA monorepo CI/CD works with 7 validation gates, Playwright E2E testing, intelligent change detection, selective deploys, and staging-to-production release workflows.
Stop LLM API costs from spiraling. A practical guide to rate limiting, per-user token budgets, exact-match caching, and cost dashboards with a deployable open-source proxy.
Stop AI-generated code from reaching production unchecked. A practical framework for detection, policy-as-code, sandboxed execution, and risk-tiered review gates.
Learn how to build production-grade MCP servers that connect AI agents to your internal databases, APIs, and tools with proper security, validation, and deployment.
Step-by-step guide to building a modular Claude Code config for VS Code with conditional rules, subagents, hooks, and stack detection.
Step-by-step React SPA monorepo CI/CD tutorial: configure 7 validation gates, Playwright E2E tests, selective deploys, staging gates, and production releases with GitHub Actions and GitLab CI.
Build and deploy an LLM API proxy with per-key rate limiting, token budgets, exact-match caching, cost dashboards, and webhook alerting using TypeScript and SQLite.