9 posts in category "ai".
Jev at the Branches: The State Machine Is the Agent
A state-machine architecture in which deterministic code owns the plan and the facts, while Jev supplies bounded judgment only at decision branches.
Jev: AI Decisions as a Typed Function Call
What I learned using TypeSafe's Jev for code review, and why its more surprising uses are browser control and generative UI.
Managing Context Windows with pi /tree: Branches, Summaries, and Subagent-like Workflows
How I use pi's /tree to manage context windows in long coding sessions, when to choose /tree vs /fork, and patterns that feel like lightweight subagents without leaving one session.
Ralph loops for SDK migrations: a case study
Part 4 of my gym-coding series: using a Ralph loop to migrate an entire SDK dependency in 81 minutes, what worked, what didn't, and where autonomous loops shine.
How my agents code when I am at the gym
Part 3 of my gym-coding setup: autonomous coding agents that keep working for you while you are out and about, and even while you sleep.
How I code from the gym — Part 2: Any AI tool, one command
Extending my phone-based coding workflow beyond OpenCode Web to support Amp, Claude Code, Codex, and any terminal AI tool using SSH, tmux, and a small session manager called vaibhav.
How I code from the gym
My setup for coding from anywhere: running OpenCode Web on Ubuntu as a systemd service and securely connecting from my phone with Tailscale.
Supercharged Code Reviews: How AI Subagents Make Human Reviewers Superhuman
Speed up your team's code reviews with AI-powered analysis that catches what humans miss and prepares focused insights, making reviewers more effective without replacing their expertise.
Having Fun with Claude Code Hooks - Make Your AI Coding Assistant Talk!
Tired of staring at your terminal waiting for Claude to finish? Let's add some personality with audio notifications and custom automation using Claude Code hooks.