Most Tech Writing Explains What. This Is About Why.
I write about what actually happens inside engineering orgs. Not the polished version.
Cut Claude Code Token Usage by 60–90%: 16 Proven Techniques
Battle-tested techniques for .claudeignore, context compression, and multi-agent task splitting that cut token usage by 60–90% without losing Sonnet's predictive accuracy.
Read article →
Why AI-Generated Plans Need Visual Review, Not More Text
AI solved the generation problem and created the comprehension problem. The bottleneck is no longer output volume. It is review surface area.
Read article →
On-Device AI Comes of Age, but Hardware Still Sets the Limits
Compact models run offline on phones, laptops, and edge devices. The bottleneck is no longer model capability. It is RAM, memory bandwidth, and thermal headroom under sustained load.
Read article →
MD vs MDX: The Decision Most AI-Agent Repos Get Wrong
Markdown is a storage format. MDX is an execution format. Every AI coding tool chose .md for agent instructions. The distinction explains why, and when MDX earns its place.
Read article →
Claude Code for Designers: Why Most Still Aren't Using AI (and the Repo That Changes That)
74% of AI coding tool users report meaningful productivity gains. Most designers are not in that number. The blocker is not skills or fear. It is project structure. A complete designer-ready Claude Code repo with DESIGN.md, design tokens, skills, agents, and a weekend setup guide.
Read article →
Airflow in 2026: The Orchestrator That Became the Operating System for Data
Comprehensive Apache Airflow analysis: open source and every managed vendor (Astronomer, Cloud Composer, MWAA), pricing at three scales, Airflow 3.0 migration, operational pain points, AI workflows, and a decision matrix for choosing the right deployment.
Read article →
Dagster in 2026: The Orchestrator That Treats Data as the Product
Comprehensive Dagster analysis: pricing, asset-centric orchestration, AI/ML pipelines, learning curve, integrations, and why treating data as the product gives teams lineage and governance that task-centric orchestrators cannot match.
Read article →
Prefect in 2026: The Orchestrator Built for AI Workflows
Comprehensive Prefect analysis: pricing, scaling, deployment architecture, integrations, learning curve, and why its dynamic Python-native control flow fits AI agent workflows better than static DAG orchestrators.
Read article →You've read everything.
No posts in this category yet.