Announcing Branchmore private beta

Branchmore is the feedback loop for engineers coding with AI. We turn the illusion of productivity into something you can actually measure and optimize.

How I use Obsidian across Claude Code and other AI tools

I use Obsidian to collect the output of Claude Code and other AI tools to feed as input in new chats to save time and improve AI memory in a learning loop.

How I Reduce AI Coding Agent Hallucinations

When I hit a hallucination that annoys me, I've trained myself to pause and run through a short checklist.

Day 2 of vibe coding in production: challenges in your team's process

Your team adopted AI coding tools and velocity went up. Here are the Day 2 process problems that emerge in production: code review, ticket quality, duplication, uptime, and security. And, what to do about each.

Measuring AI coding adoption: What I learned as a manager

Increasing AI adoption is common objective for engineering managers. Beyond qualitative surveys, what else can we do?

Vibe Coding in production: what's holding us back?

Vibe coding techniques need to be adapted when you work on production applications with AI. I walk through some challenges and solutions that I've found helpful on real projects.

Is Claude Code 5x Cheaper Than Cursor?

I ran 12 side-by-side experiments. At the same $200/month, Claude Code delivered roughly 5x more agent-hours. Here's the data, methods, and nuances.

How I got to 3 parallel Claude Code agents + past 16% utilization

I was stuck at 16% Claude Code utilization. Here's how I set up 3 parallel coding agents working on separate projects using git worktrees.

I switched from Cursor to Claude Code and got stuck at 16% utilization

I thought I overpaid for Claude Code. I started a journey that taught me about different pricing paradigms and how to increase my token utilization effectively.