How the system works

The Directory is a table. Each row is one thing the system can do for your business: send a text from your number, book a slot in your calendar, create an ad, read a web page, take a screenshot of your Mac. If an action is not in the table, the system cannot do it.

Each row stores everything needed to run that action: where it runs, what inputs it needs, what it returns, and every way to call it. Changing a setting is typing in a cell. Files added to the system’s folder are added to the table automatically.

One row per action. Each row has one column per way of calling it, and each of those cells holds the complete request (method, address, headers and body) that runs it, followed by the full response from the last run.

The Ledger is a record of everything the system does: every message sent and received, every action run, every change, every AI model’s answer, and every request that was refused. Nothing in it is overwritten. To find out what happened, you read it.

Each entry stores the full request and the full response. Each entry also stores a fingerprint of the entry before it, so if anyone changes an entry later, the change shows up. Refused requests are recorded the same way as completed ones.

Every payload in or out is a Ledger row. Each action appends one row containing a SHA-256 hash of the previous row; nothing is updated in place. An action counts as working only when the declared surface itself ran and five things are stored for that run: why it ran, the exact request written before it ran, the confirmation, the exact response, and the record.

You decide what the assistant may read (your calendar, your messages, your price list), what it may do (reply, book, invoice), and whom it may answer. A refund can be limited to $500, for one customer, for ten minutes. Ads are created paused. When someone asks, the assistant says it is an AI assistant.

Each action carries its limits: an amount, a time window, a channel, an account. A request outside them is refused, and the refusal is written to the Ledger like any other entry.

A scoped permission is issued for one task, with a limit and an expiry, and stops working when the task is done. With no permission, nothing runs; the refusal is a Ledger row.

AI agents are separate programs, each running an AI model. You give one a task by typing it into a row of a shared spreadsheet; it does the work and writes its answer in the next column. A task is closed only when there is a real answer.

Each agent has its own Directory and its own Ledger, and each of its settings is a spreadsheet cell: type in the cell to change it. When a task fails, a new task is created that says what went wrong.

Each agent is its own Cloudflare Worker with its own storage and keys, connected through a shared workbook. Agents have changed and deployed their own code and added their own tests; work is accepted when its tests pass against the live system.

The Console app runs on iPhone, iPad and Mac. It shows the Directory, the Ledger and your AI agents, and lets you message the agents.

The Ledger opens in tabs: conversations, sessions, changes, events, tasks, traffic, AI models, actions and analysis. Every entry opens to its full content.

The app is a view of the same data: the Directory, the Ledger, the connected agents and the terminals. It reads the system; it does not keep a separate copy.