Family Chore Buddy: A Bank for Kids That Isn't a Bank
Why I built a simple money tracker for my kids, what it teaches them about saving, and how it went from an old conversation to a live product in a week.
Writing desk
Ideas from the work.
Curated field notes about operating systems, product judgment, practical AI, and what I'm learning as I build Loomfield.
Editorial line
Concrete over theoretical. Systems over tools. Lessons earned by trying to make real work easier to run.
Setting Up an App by Talking to It
What happened when I gave Family Chore Buddy an MCP server, so any AI assistant can set up a family, keep it current, and report on it in plain words.
Build Log: Workflows and a Hub That Kept Freezing
Visual workflows for building automations without code, and a two-week hunt for the reasons the hub kept freezing as it grew.
Build Log: Loomfield Leaves the Room
The first invite-only alpha builds for Mac and Windows, the install bugs my own tests missed, and a rebuild of how decisions are tracked.
Build Log: Stop Shipping Dark
Two weeks teaching Loomfield to learn reusable tools from its own work, fixing a status bug properly, and ending the habit of shipping everything switched off.
Build Log: The Audit That Audited Itself
A reusable audit for checking whether AI-finished work is really finished, the bugs it found in itself, and cutting the cost of re-sending context.
Build Log: Making the System Keep Its Own Books
Two weeks turning record-keeping from a rule agents follow into something the system checks, plus much faster recall and a hard look at routines.
Build Log: One Version of the Truth
Three weeks moving Loomfield's memory onto structured records, rebuilding Mission Control around honest screens, and having more than one model check the work.
Preparing Loomfield for the Public
What changes when a private-beta AI work system has to become clear, trustworthy, and useful without its builder in the room.
Small Context, Serious Work
How Loomfield uses focused retrieval, smart micro-sessions, and the smallest capable model to spend context where it actually improves the work.
On the Desk: Teaching the Vault to Run the Work
A June workbench update on making the vault leaner, better routed, and responsible for carrying useful results into the next session.
Building Loomfield: an operating system for AI work
Why the next useful layer for AI is not a better chat window, but a shared brain, durable work, and controls that earn trust over time.
From Helpful Chats to an AI Operating System
What the first real limits of a shared AI vault reveal about rules, enforcement, coordination, and the missing operating layer.
Designing a Vault for AI Work
Early notes on building a durable Markdown home for projects, decisions, reusable instructions, and the context an AI assistant should carry forward.