What the system can doImages and video
One family of actions
Images and video
Make and edit images and short videos from a written description, and keep every file at a lasting link.
Pictures and videos are made by the image and video models you choose and stored with a link that does not expire.
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.
Make images
—Make an image from a written description with the image model you choose, or with two models side by side, and get back a lasting link.
Edit images
—Change an existing image by describing the change in words.
Make video
—Start a video from a written description, then collect the finished file.
Store, file and deliver
—Keep reference images and finished work in storage with a lasting link, file them in an image library, deliver finished files to whoever asked, and check this month’s usage.
Read text in an image
—Pull the printed text out of an image or a screenshot.
Uses
What a business uses these actions for.
Examples of the work these actions do. They describe uses, not results.
Make several versions of an ad image from one written brief.
Change the background of a product photo by describing the change.
Pull the text out of a photo of a receipt or a sign.
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.