What the system can doEverything else
One family of actions
Everything else
Small utilities, the system’s own code, requests and offers between buyers and providers, and rows that test the system.
Actions that support the other families, and ones that do not fit any of them.
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.
Small utilities
—The time, upper and lower case, a fingerprint (SHA-256 hash) of a piece of text, pattern matching, and totals over a dataset that never reveal a single record.
The system’s own code
—Read and change the system’s own source files and GitHub issues, search the code by meaning, and stop two AI agents editing the same file from overwriting each other.
Requests, offers and results
—Record what someone wants and what their AI may spend on it, collect and rank offers from providers, hold payment until the task closes, and publish results computed from Ledger entries that anyone can recompute or dispute.
Other installations
—Send signed messages to an installation at another address, and publish this installation’s public identity.
Test rows
—Rows that exist to test the system: each one checks that a feature still works.
More
—Other single-purpose actions.
Uses
What a business uses these actions for.
Examples of the work these actions do. They describe uses, not results.
Most of these are used by the other actions rather than asked for directly.
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.