I Had 56 AI Agents Installed. I Was Using One.
How I audited my Claude Code setup with real usage data, archived 90% of it, and got better results for fewer tokens. A cleanup method for product people.
Read Post
Productivity
Let's talk about...
Productivity.
Productivity
Loop Engineering: Stop Prompting Agents, Start Designing the System That Prompts Them
Loop engineering replaces you as the person who prompts the agent. You design the system that does it instead — five pieces, one memory, and a verifier you trust.
Read Post
Productivity
I Made Claude Opus 4.8 Manage Another AI Agent While I Worked
How I built a ticket-based workflow where Claude Opus 4.8 orchestrates OpenCode, cutting token waste while preserving review, visibility, and control.
Read Post
Productivity
AI Pipelines: How I Built Systems That Work While I Sleep
CareerOps, content curation, and Obsidian automation: three AI pipelines that replaced months of manual work with systems that run on their own.
Read Post
Productivity
Designing in Words: How AI Turned UX Designers Into Their Own Frontend Engineers
The gap between your Figma file and what ships has always been a negotiation. AI just handed you the power to end that negotiation on your own terms.
Read Post
Productivity
Claude Code Skills: The Professional Layer Most Users Ignore
You already use Claude Code. But if you're still typing the same prompts session after session, you're burning time on infrastructure instead of work. Here's how to build the system that professionals run on.
Read Post