Why your AI agent costs 10x more than you think
6 min read
Most AI agent cost problems are workflow problems. How I used one OpenClaw blog pipeline to find retries, prompt bloat, and hidden setup waste.
Blog
Open Source LLMs in 2026: How to Pick the Right One
12 min read
How to choose the right open source LLM in 2026 based on workload, deployment needs, cost, and when self-hosting actually makes sense.
Running OpenClaw in Production With a Patch Overlay
7 min read
Run OpenClaw in production without forking it. Use a patch overlay to ship urgent fixes fast and keep upgrades clean.
The Hidden Token Tax of MCP
7 min read
MCP adds a hidden token and latency tax because models must read tool schemas and manage multi-step tool loops before they can answer.
How to Use Spec Kit with Claude Code and Linear
5 min read
Spec Kit works best at the feature-planning layer, where it preserves shared context without forcing teams to replace their story-level workflow.
Dispatch, Cowork, and the Two Types of Remote Tasks
8 min read
Sandbox tasks vs code tasks, three types of automations, and how to build pipelines that span both environments from your phone.
The Five Layers of a Remote Mac Agent Setup
9 min read
A framework for understanding the tools you need to run Claude Code and Cowork from your iPhone, and how to debug when things break.
Running Claude Code on Your Mac from Your iPhone
9 min read
How to set up Tailscale, Termius, and Mosh for persistent Claude Code sessions from your phone, plus the Remote Control combo workflow that makes it practical.
AI Follows Your Instructions 70% of the Time: How to Enforce the Rest
10 min read
AI instruction files work 70% of the time. Close the gap with hooks, automated validation, and team governance strategies.
How to Give AI Assistants a Map of Your Messy Codebase
10 min read
Monorepos, legacy migrations, mixed framework versions. Here's how to configure AI coding assistants when your codebase doesn't follow one set of rules.