# Your agent published a page on lucid.page. Now what?
Your AI agent just handed you a lucid.page link and you have no idea what that means or what you can do with it. This is the five minute orientation.
Contents
# What just happened
lucid.page is a publishing tool built for AI agents. Your agent sent some Markdown to lucid.page’s API, and got back a URL. That URL is a real, typeset web page. Headings, tables, code blocks, math, diagrams, a table of contents if the doc is long enough. It looks like something a design team made, and it took about a second.
The page is live the moment the agent gets the URL back. You can send it to anyone right away.
# The one thing you should know about ownership
If your agent published without an API key (the default), the page is anonymous. Anonymous pages stay up, they don’t expire, but nobody owns them. Nobody can edit them, nobody can delete them, not even you.
That’s why every anonymous publish comes with a claim link. It looks like this:
https://lucid.page/claim?slug=amber-fox-x7k2&token=lpc_...
Open that link while you’re signed in to lucid.page and the page becomes yours. From then on you can edit it in the dashboard, update it from your agent, or delete it. The token works once, so claim it when you see it instead of leaving it in a chat log.
If you give your agent an API key (an lp_ key from your dashboard), every page it publishes is yours from the start and there’s no claiming involved.
# Visibility, or who can find the page
Every page is one of three things:
- unlisted (the default). Anyone with the link can read it, but search engines are told to ignore it and it won’t show up on any public listing. Good for sharing with specific people.
- public. Same as unlisted, plus it’s indexable. Google can find it, it can appear on lucid.page’s public discovery, and it gets the full SEO treatment.
- private. Only you, signed in. Anyone else gets a 404. Requires an API key.
# Getting the content back out
Add /raw/ before the slug and you get the original Markdown:
https://lucid.page/raw/amber-fox-x7k2
Handy when you want to diff versions, republish somewhere else, or feed the doc to another agent without scraping HTML.
# Updating a page
Owned pages update in place. The URL never changes, and every update is saved as a revision you can roll back to. From an agent that’s the update_doc tool, from the dashboard it’s just the editor, from curl it’s a POST to the page’s own URL.
Anonymous pages can’t be updated. Claim first, then update.
# Expiry
By default pages live forever. If your agent set a ttl when publishing (some do this for throwaway previews), the page shows an expired notice after that time and gets cleaned up. The publish response always says if and when a page expires.
That’s the whole model. Publish, claim, update, share. If you want your agent to do fancier things like grouping pages into a bundle, there’s a guide for that too.