Series
The Parallel Developer
A five-part series on running multiple features in flight simultaneously using git worktrees, OpenSpec, Beads, and AI agents.
5 parts · first published
- 01
Why Agentic Coding? It's Not About the AI
Agentic coding isn't a smarter autocomplete. It's a workflow shift — and the structure you build around the agent is 90% of the value, even without the AI.
· 5 min read - 02
Git Worktrees: Branches as Places, Not States
One repo, three running apps, zero context switches. Git worktrees have been in git since 2015. Almost nobody uses them. Here's why that's a mistake.
· 5 min read - 03
OpenSpec: Write the Contract Before the Code
Freeform prompts to an agent produce freeform code. Three commands and a human review step change that. Misunderstandings surface at proposal review, not after an hour of wrong code.
· 6 min read - 04
Beads: A Local-First Task Graph for Developers and AI Agents
GitHub Issues is great for tracking work across a team. Beads is great for the local development loop — and for the AI agents running inside it. It's the same data, in the same repo, queryable with jq.
· 5 min read - 05
AI Agents That Work: Give Them Structure, Not Just Prompts
Agents don't fail because they're dumb. They fail because they're given ambiguous context. This is how the four tools in this series eliminate that ambiguity.
· 6 min read