Technical Insights

Eighteen months with AI agents and Festival: 3,723 merged PRs, work across 151 code repositories, and hundreds of plans. How I kept that much work moving.

Private repositories burn GitHub minutes. Here is how to run Linux, Windows, and macOS jobs on the computer you already use.

I use AI to help write blog posts and recently started using Humanizer to improve draft readability. Here’s how I use its hz CLI and decide which edits to keep.

I ran a manager-worker agent team on 67 real tasks. A single session would have done the work better. The failure modes are structural.

Agent memory should be files in git, next to the work they describe, not rows in a vendor database.

A gate an agent waves itself through is not a gate. Quality gates for agent work have to be decisions against artifacts.

The unit of work is no longer a prompt. It is a loop with a driver, a body, exit conditions, and failure modes.

Production got cheap. The bottleneck moved: holding fragments together until the work is actually done.

After Véra on a 1st-gen Scribe (5.19.5): linux/arm on /mnt/us, Wi-Fi SSH, git, a GL.iNet lab tap, and Notes Sync to push stock notebooks to a git remote I control.

Nine months of running Festival on real work, measured from the logs.

How I used Festival to build the Obey Agent Economy at ETH Denver 2026: eight repos, six chains, a vault that can refuse a trade, and 2nd place at Chainlink Convergence.

A battle-tested workflow for using Claude Code to manage large-scale projects with parallel AI agents working like a distributed engineering team