Core observability concepts and the structured events model from Honeycomb's official docs, with a practical comparison of open source alternatives including Jaeger, Zipkin, SigNoz, and Pinpoint
An analysis of Stripe Minions' structured workflow that produces 1,300+ AI-written PRs per week, and the adversarial development technique that dramatically improves agent reliability
A deep analysis of the Claude Code Skills system through the lens of the Excalidraw diagram skill — from the philosophy of visual argumentation to building your own skills.
A complete guide to Claude Code automation covering the full skill lifecycle from creation to deployment, three approaches to cron-based scheduling, and remote control via Dispatch
27 tips drawn from 500+ hours of Claude Code experience, organized by beginner, intermediate, and advanced levels with practical application notes
Migrating image storage from the local filesystem to AWS S3, applying Diffs branding, and a series of UI stability improvements across 31 commits
An analysis of why LlamaIndex abandoned the RAG framework model in favor of LiteParse — a single focused tool — and what it signals about the structural shift in the AI developer tooling ecosystem
A deep dive into Anthropic's long-running agent blueprint and how harness engineering provides a systematic quality management framework for AI agents
How Superpowers grew from 69k to 110k GitHub stars, a practitioner's critique from a Korean YouTuber perspective, and an analysis of how it complements HarnessKit
Adding DCF sensitivity analysis, portfolio risk metrics (VaR, beta, correlation), and a news/macro analyst as the sixth expert in the signal pipeline, plus DART integration
