Blog
Articles on AI engineering, production ML, and building real systems.
See how CRISP-DM still guides AI engineers in 2026, translating each phase into practical workflows for LLM apps, RAG pipelines, and production AI systems.
An incident story: how I accidentally wiped our AWS RDS production database and deleted snapshots by letting Claude Code touch production infrastructure.
Learn what an AI engineer is in 2026: responsibilities, skills, tools, and real-world use cases based on analysis of 1,000+ AI engineer job descriptions.
How to join AI Engineering Buildcamp: individual enrollment, team discounts, company L&D budgets, student discounts, PPP pricing, and scholarships.
Learn how I built the ChatGPT Data Viewer, a local app that searches and visualizes your ChatGPT export with statistics and a GitHub-style activity view.
A practical definition of the AI engineer role: what they do, how they differ from ML engineers and data scientists, and what it takes to ship AI-powered features from prototype to production.
Learn how I built SQLiteSearch, a lightweight, single-file Python library for fast text and vector search with SQLite (no Docker).
I unpacked the mysterious /home/oai/ directory that ChatGPT can zip on command and found not leaked OpenAI infrastructure, but a sandbox of document, slide, and spreadsheet “skills” that reveals how the new cross-vendor agent skills standard works in practice.
A story about how I built and maintained a Slack moderation bot for an 88k-member community using AI and AWS Lambda.
Learn how I built a Telegram-based writing assistant that uses Claude Code to transcribe voice notes and convert brain dumps into structured Markdown, saved and versioned in a GitHub repo.
I built funny projects with custom Claude Code slash commands (/kid and /parent), then explored stop hooks, the Ralph Wiggum plugin, and a Python-based continue loop to keep Claude coding continuously.
How I merged a DataTalks.Club Wrapped feature by opening a PR from a tram stop, iterating with Copilot from my smartphone, and deploying via CI/CD.
I built a fully automated system that takes photos of everyday objects and turns them into illustrated horror stories, complete with audio narration and Spotify podcast episodes. Here's how I did it.
I hadn't updated my personal website since 2012. Using AI tools like Lovable and GitHub Copilot, I rebuilt it from scratch in under 10 minutes. Here's exactly how I did it and what I learned.