Deep-dives for AI builders
Long-form technical write-ups that go past the demo — what we tested, what broke, and what we would ship to production.
- AI Voice Agents
Best AI Voice Agent Platform in 2026 (Retell vs Vapi vs ElevenLabs, Tested)
I built the same AI receptionist on 6 AI voice agent platforms, fed them one identical call, and measured speed, interruptions, setup, understanding, naturalness and cost.
Read - Multi-Agent Systems
How I Built a 9-Agent AI Platform With Two Codex /goal Commands
I didn't write the code — I wrote the spec. Twice. Here's exactly what Codex CLI built: 9 AI agents, a FastAPI backend, a Next.js dashboard, and 230,000 tokens.
Read - AI Agents
Context Engineering — The 5-Layer Architecture Every AI Builder Needs
Your AI agent doesn't fail because the model is weak. It fails because the context is broken. The 5 layers of context architecture and 5 rules for production agents.
Read - AI Agents
GitHub PR Security Reviewer — Automated Claude Security Review for Every Pull Request
A GitHub Action that reviews every pull request for security vulnerabilities using Claude. Posts findings, severity ratings, and remediation advice in under 60 seconds.
Read - Prompting
ChatGPT Image Prompts That Actually Work
40+ prompts across seven capabilities — precision, multilingual text, photorealism, art styles, aspect ratios, real-world intelligence, and multi-image workflows.
Read