Blog
Notes on agentic developer platforms, MCP, evals, and what makes AI coding tools ship inside large engineering orgs.
31 posts
Opinions & Analysis9 min readClaude Code vs Codex vs Cursor (and Why It Doesn't Matter)
The honest Claude Code, Codex, and Cursor comparison — and why your AI platform strategy matters far more than which coding agent you pick this quarter.
Problem & Solution6 min readBeat Developer Burnout with AI-Powered Task Scoping
Stop drowning in task management. Learn how AI agents can automatically scope your work, research approaches, and maintain a stress-free pipeline.
Tutorials & How-Tos4 min readEscape AI Platform Lock-In with a Portable CLI Toolkit
Stop rebuilding AI tools for every platform. Build a portable CLI toolkit with centralized config that works with Claude Code, Cursor, or any agent.
Tutorials & How-Tos7 min readBuild Your Own Voice Assistant: Escape Alexa and Google
Tired of creepy always-listening devices? Build your own private voice assistant with local wake words, any LLM, and custom Python tools on a Mac Mini.
Tutorials & How-Tos5 min readAdding Eyes to Your AI Workflows with Gemini
Use Gemini's overlooked image detection features to find objects, extract precise bounding box coordinates, and build truly context-aware AI applications.
Tutorials & How-Tos4 min readAI Content Pipelines: From Text Prompts to Images and Video
Build automated content pipelines using Claude Code skills and OpenAI APIs. Generate character images, convert to Discord emojis, and animate with Sora.
Opinions & Analysis9 min read2025: The Year AI Development Grew Up
From reasoning models to agentic CLIs, 2025 transformed how we work with AI. The timeline of our shift from model-centric to agent-centric development.
Guides & Fundamentals7 min readSkills: One Agent Toolbox That Ends MCP Micromanagement
Stop juggling MCPs across projects. Claude Code Skills let you build one universal toolbox that travels everywhere with zero context overhead until needed.
Tutorials & How-Tos5 min readWhy I Stopped Reading AI's Code: Visual Proof Instead
Build review agents that prove AI code works using Playwright screenshots, video recordings, and visual diffs rather than manually reviewing each line.
Tutorials & How-Tos8 min readAI-Powered Bullet Journaling with Claude Code
Transform bullet journaling into an AI-assisted productivity system that adapts to your mental state, helps you recover from setbacks, and removes shame.
Tutorials & How-Tos4 min readAI Sandbox Environments: Safe AI Code Execution
Move past rm -rf nightmares by running AI-generated code in isolated sandbox environments. Learn how e2b.dev enables safe, parallelized development workflows.
Tutorials & How-Tos5 min readAI Security Workflows: Automated Vulnerability Management
Turn security from a reactive burden into an automated pipeline. Use Claude Code's security review and package audits to build self-healing codebases.
Tutorials & How-Tos6 min readBuilding Reliable AI Workflows: How to Handle Millions of Agent Iterations
Learn how to engineer robust AI agent systems that scale to millions of iterations through state isolation, validation gates, and parallel consensus patterns.
Guides & Fundamentals6 min readPrompting is Everything: The One Skill You Need to Master AI
One piece of advice for getting started with AI engineering: master prompting. Learn why the prompt is the foundation of everything you build with LLMs.
Tutorials & How-Tos6 min readSkills Over MCPs: Context-Efficient Agent Capabilities
Claude Code Skills provide MCP-like capabilities with zero context overhead. Scale to thousands of tools without bloating your agent's context window.
Guides & Fundamentals7 min read4 Claude Code Primitives: Commands, MCPs, Subagents, Skills
Master Claude Code's four primitives—slash commands, MCPs, subagents, and skills. Learn when to use each one and how to compose them into powerful workflows.