What the system changes for a business, and which part does it.

Nothing changes on your phone. Your customers keep the thread they already have with you, your caller ID matches your listing and your invoices, and the assistant replies from the same number you have used for years.

We test whether your line can pass Apple's verification. Most mobile carriers can. Hosted VoIP and some ported lines cannot, and we tell you before you pay anything.

Your number is registered as an iMessage identity on hardware we operate for you. Apple sends a one-time code to your line; you read it to us on the call.

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.

Dispatch is a single web address. You, your staff, a spreadsheet, an iPhone Shortcut or an AI model send it the name of an action and its inputs. It finds the action in the Directory, checks your permissions, runs it on the right computer, sends back the result, and writes an entry in the Ledger.

Because every request goes through the same address, the same permissions apply whether a request comes from a text message, a link, a spreadsheet cell, a Shortcut, the command line or an AI model, and every request is recorded the same way. One action can be switched off in one place.

Every action is invoked as an HTTP POST of {"key": "<action name>", "args": {…}}. REST, MCP, spreadsheet formulas, text tags and webhooks are different ways of making that same request. Actions run on Cloudflare servers, a Mac, an iPhone, a browser, a virtual machine or a phone.

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.

AI models such as Claude, ChatGPT, Grok and Gemini can all use the same Directory of actions, with the same permissions, and everything they do is written to the same Ledger. Changing which AI model you use does not mean rebuilding anything.

Every AI model sees the same actions and limits. What each one was asked, what it answered, and what it cost are entries in the Ledger, so models can be compared on real use.

The system is an MCP server (MCP, Model Context Protocol, is the standard way AI apps connect to outside tools): every Directory row is an MCP tool, a function call and a REST endpoint at the same time.

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.

Customers and leads are told it is an assistant when they ask, and it hands to a person the moment the conversation goes somewhere it shouldn't.

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.

A library of research articles. Every claim in an article links to its source, or is marked as having no source. Every change to an article is kept.

Any claim can be disputed on the page where it appears. An AI model can read the same article as structured data.

Each article is JSON: its claims, their sources and its revisions. The library is stored like everything else in the system.