What the system can doGoogle
One family of actions
Read and create Calendar events, search Gmail and Drive, read and write Sheets, keep Tasks, and look up places, routes and weather.
These actions use the Google account you connect, with the access you grant it.
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.
Calendar
—List calendars, read upcoming events or the events between two times, and create an event.
Gmail
—Search Gmail with Gmail’s own search words, and read a message or a whole thread.
Drive and Docs
—Search Drive, read a file’s details, and read a Doc, a Sheet, a PDF or a text file as text.
Sheets
—Read and write ranges of cells, add rows, list a spreadsheet’s tabs, run Apps Script (Google’s scripting for Sheets), and keep the Directory in step with a Google Sheet in both directions.
Tasks
—Read Google Tasks lists and their open tasks, add a task, and copy the system’s open tasks into Google Tasks.
Maps
—Find places and businesses with their addresses, ratings and hours, get a driving route with distance and time, and read the weather for a place.
Search everything at once
—Search Gmail, Drive, Docs, Sheets, Calendar and Chat in one request.
Google Cloud and developer docs
—Query BigQuery (Google’s data warehouse) read-only, list Google Cloud projects, search Google’s developer documentation, check which Google account is connected, and read from any other Google address.
Uses
What a business uses these actions for.
Examples of the work these actions do. They describe uses, not results.
Book a job into Google Calendar and confirm it by text.
Add each new lead as a row in a Google Sheet.
Look up the drive time to a customer before quoting a visit.
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.