What the system can doDirectory and sheets
One family of actions
Spreadsheets and the Directory
Find, add and change the actions themselves, and work with them from spreadsheet cells.
The Directory is the table where each row is one action the system can run. These are the actions that work on that table.
Live, read from this site just now.
The groups in this family, counted just now: — actions
This family among all — actions in the Directory, one square each
Each action is one row in the Directory, sorted into this family by the start of its name.
What it can do
What the actions in this family do, group by group.
Each card is a group of actions that do similar work. The number on each card is how many actions are in that group right now.
Switch to “For your developer” to see the real name of every action.
The real name of every action, read from the Directory just now. Names that contain a supplier’s name are left out of the lists, and still counted.
Find an action
—Search the Directory in plain words, read any row in full (what it does, what it needs, where it runs, every way to call it), and browse the rows by category.
Add and change actions
—Add a row, change or delete one, and add a line to an assistant’s instructions or memory.
Import actions from elsewhere
—Read another program’s documentation, the tools offered by an MCP server (a tool server AI apps connect to), a skill file or a code repository (a project’s files and their history), and propose a new row for each action found, checked against the rows that already exist.
Records and settings
—Read and change stored records and settings one field at a time. A change is written only if nobody changed the record since it was read.
Spreadsheets
—Make a spreadsheet tab that shows live rows from the Directory or the Ledger, add columns and filters, type a request in a cell and get the answer in the next cell, and run a sheet’s script.
Uses
What a business uses these actions for.
Examples of the work these actions do. They describe uses, not results.
Find the right action by describing it in plain words.
Change an action’s limit once; every way of asking for it follows.
Run actions from a spreadsheet: type the request in one cell, read the answer in the next.
How it is run
How any of these actions is run.
The same way as every other action in the Directory: one request, the same permissions, one record.
You don’t have to pick an action yourself. You text what you want; the AI assistant picks the action and runs it within the permissions you set. The result comes back to you, and the request, the result and who asked are written to the Ledger, the record of everything the system has done.
Every action is one row in the Directory, and each row can be run — ways: a text, a link, a spreadsheet cell, an iPhone Shortcut, a command, or an AI model’s request. Every way goes through dispatch: one web address that looks the action up, checks the permissions, runs it on the right computer, sends back the result and writes a Ledger entry. The same action answers every way, under the same limits.
Dispatch takes an HTTP POST (a standard web request) of {"key": "<action name>", "args": {…}}. The same key works over the API (the web address your software calls), MCP (Model Context Protocol, the standard way AI apps connect to outside tools), the command line (CLI), a webhook (an address another program posts to), a spreadsheet cell or a Shortcut. A token (a key or a link) can be limited to exactly the actions you allow; every call, and every refusal, is a Ledger entry.
// One action from this family, as dispatch receives it
{ "key": "…", "args": { … } }Ask for this.
The text below opens ready to send. Add a line about your business, and I’ll reply with what this family of actions would do for it.
Every family
Everything else the system can do.
Every family of actions, with how many actions it has right now.