What the system can doPermissions
One family of actions
Permissions and approvals
Links that allow one action, approvals on your phone, rules that refuse requests, and the people and devices allowed in.
Permissions decide what may run, for whom, and within what limits. A request outside the limits is refused, and the refusal is written to the Ledger.
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.
Links that allow one thing
—Make a link that lets whoever holds it run exactly one row, or a few, for a set time or a set number of uses; see what a link allows before it is used; switch it off at once. A chat or a session can be shared the same way.
Ask a person first
—Stop before a send and wait until someone says yes on their phone; approve or refuse from the phone.
Block and limit
—Add rules that refuse matching requests before they run, pause a rule without deleting it, and cancel every link and device of one person at once.
People, devices and accounts
—Create an account for a person from a one-use invite, register, trust or remove a device, and see who can reach what.
Lend an account for a set time
—Give someone limited control of an ad account or a browser profile for a set number of hours, with the allowed actions listed, a spending limit, and a snapshot taken before and after.
Written rules and decisions
—Keep the written rules the system and its AI models follow, record decisions with the reasons and evidence behind them, and record reviews of those decisions.
Uses
What a business uses these actions for.
Examples of the work these actions do. They describe uses, not results.
Give a contractor a link that runs one action, for one week.
Wait for a yes on your phone before a message goes out.
Cancel every link and device a former employee held, in one step.
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.