The AI Pilot Scoping Starter Kit
Choose an AI use case, match the problem to automation, AI, or an agent, define a small pilot, and decide how you’ll measure it.
Pairs with How to Actually Get AI Working at WorkStarter Kits
AI workflow starter kits for operators.
Self-contained guides that pair with my posts, each at three levels: a manual version for a plain chat window, the full folder-based setup for Claude Code or Cowork users, and a section written for your AI agent to build from directly. Free, no signup, and the manual level needs no technical background at all.
The kits
Each kit includes a guide you can read on the site and the complete Markdown file you can hand to an agent. Start manually, build the folder-based version if you use Claude Code or Cowork, or give the file to your agent and ask it to set up the system with you.
The Strategy Grounding Kit
A one-page strategy doc and a decision-record template that give AI something real to execute against. AI can only move at the speed of your strategy if your strategy is written down.
Pairs with Executing at the Speed of StrategyThe Judgment Folder Starter Kit
A rulings log that turns your one-off corrections into standing rules, so you stop making the same edits twice. Starts as a single document; grows into a folder your AI tools read before you see a draft.
Pairs with Executing at the Speed of StrategyThe One-Lane AI Review Starter Kit
Have a model that didn’t write the draft check it against one rule you care about, and keep the verdicts where you can reread them. The smallest working version of the review system that built this site.
Pairs with the website-build postThe AI Operating System Starter Kit
Build the layers of your AI setup that persist between sessions: verified facts, standards, boundaries, a rulings log, routing, and automated checks. Four levels, from one pasted file to a configured agent platform.
Pairs with How Prompts, Context, Harnesses, and Models Shape AI OutputThe Files-First Starter Kit
Four files that stop you from re-explaining yourself every session: who you are, what is live right now, your standards, and your corrections. No platform required, just a chat window.
Pairs with How I Turned My Knowledge Work Into Code With AI AgentsThe Context Capture Starter Kit
Four pieces that keep your AI setup current on its own: a startup step that loads state, a scheduled routine that captures email, chat, and meeting context into a project, a corrections loop, and stale-context prompts.
Pairs with How I Turned My Knowledge Work Into Code With AI AgentsThe Project Agents Starter Kit
Structure for running more than one agent at once: one agent per project with its own memory and task states, a coordinator that routes and never does the work, model routing, independent review scaled to what is expensive to get wrong, and a board.
Pairs with How I Turned My Knowledge Work Into Code With AI AgentsMore to come as posts are published. Subscribe on Substack →