What the system can doWeb and pages
One family of actions
Web search and pages
Search the web, read any page, pull public data, publish web pages, and write articles where each claim links to its source.
Searches and page reads leave from a home internet connection, so sites that block data centres still answer.
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.
Search the web
—Search the web and get back the best pages with their text, not only a list of links; search Hacker News and public code repositories.
Read any page
—Fetch any web address and get back its content, open it in a real browser so its scripts run, read a Wikipedia summary, and see which internet connection the request leaves from.
Public data sources
—Public records you can query: recent earthquakes, software packages and their download counts, AI models ranked by downloads, public APIs (interfaces programs use to exchange data), MCP servers (tool servers AI apps connect to), the advertising files that say who may sell a site’s ad space (ads.txt, sellers.json), and lists of tracking companies.
Publish web pages
—Create, edit and delete web pages; every edit keeps the earlier version, so any page can be put back.
Write and check articles
—Write, edit and publish articles in the research library, where each claim links to its source or is marked as having none; let AI models add sources, questions and objections to a claim; queue articles to be written.
Uses
What a business uses these actions for.
Examples of the work these actions do. They describe uses, not results.
Read a competitor’s public pages before a meeting.
Publish a page, and put back the earlier version if an edit was wrong.
Keep a library of what you know, with a source for every claim.
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.