The same method, in a small business
Software a small business and a household run on.
The same approach as work, at a scale I can watch closely: a real rental business, a household's finances, and a second memory vault. Identity, data governance, cost caps, and a human approving what AI proposes.
A rental app for a family member
A family member runs a ~50-property rental portfolio, mostly from a phone. I built the app that runs it. It tracks expected rent against received rent, leases and tenant history, move-in and move-out photos, improvements, and bills. It never moves money. Payments stay on the rail they were already on, and the app tracks and flags.
Two AI pieces, both fenced. The importer reads a messy spreadsheet and proposes rows, and a human approves every row before anything is saved. The assistant answers questions over the ledger and may never invent a number, because every figure it says comes from the database rather than the model.
Cost is fenced too. Market rent data comes from RentCast behind a cache with a self-enforced monthly ceiling that is checked before every outbound call, and the remaining quota is visible on screen. The rule I designed to is that no button on screen can cost money. Access uses Clerk, scoped by organization, so the identity provider authenticates and our own database decides what that person can see. It runs on a single Cloudflare Worker with D1, R2, and a monthly cron job that writes to an audit table.
The vendor work mattered as much as the code. Three data vendors were rejected on license terms rather than capability, RentCast was kept under a caching design its license permits, and Street View imagery was dropped once it was clear the license did not allow storing the image. It is live at myonealproperties.com.
A household finance assistant
A private finance app for our household: balance sheet, cash flow, recurring payments, receipts, and a chat assistant. A deterministic engine doing integer-cent math owns every number on screen. The model explains and navigates. It does not calculate.
The privacy rule is enforced by the operating system, not by instructions. The language model runs locally under its own isolated OS user account, so real financial data never reaches a cloud model. Sign-in is passkeys and Face ID. The bank and brokerage connectors sit behind a gate that fails closed, so missing configuration means it refuses to connect rather than quietly falling back. It has a self-deploying release pipeline, so fixes ship without me sitting at a terminal.
A second memory vault
The AI memory system I built for work is a method, so I run it twice. The personal vault holds 25 documents, loaded by the same nine hook scripts and routed by folder, with a firewall between work and personal context so neither loads in the other. It writes its own session summary at the end of every session.