Vercel UI SDK builds the page, and lets agents use it
- Components on this page
- 0 of 0 kinds
- Agent steps run
- 0
- Steps held for a person
- 0 by
data-agent-confirm
Ghost.exe presents
See what you're about to tell an AI, before it does.
This is the hosted demo. Everything runs in your browser: a pretend model answers, and you're the approver. Get the code to connect a real model and real approvers in Deliverd. We count page visits with Vercel Web Analytics (no cookies); nothing you type or drop is part of it.
Vercel UI SDK builds the page, and lets agents use it
data-agent-confirmDeliverd screens it, and asks a person
Drop text files here to check them too.
Notes, CSVs, logs, code, .env files. Up to 1 MB each.
You can change this yourself. An agent has to ask a person first.
Verdict
Screener doesn't look for people's names yet. Patterns can't find them; a model can. How
The approver's phone
What happened
Watch an agent try
An agent drives this page through Vercel UI SDK's agent bridge. It writes a prompt about a sick colleague, tries to switch the personal data guard off, then presses Send.
ChatGPT and Claude both let you download everything you've ever said to them. Drop that export here and Screener counts the email addresses, card numbers, keys and the rest that went in, and in which conversations. The file is read in this tab and never uploaded. It shows kinds and counts, never the values.
Drop your export here (the .zip, or conversations.json)
data-agent-confirm mark, so an agent that tries to loosen them waits for a person. A browser's own agent can use the page through WebMCP, under the same rule.A net, not a certificate. Structured identifiers are found well; names are not found at all without a model. Text with placeholders in it can still be personal data. Use it to send less, never as proof a prompt was clean.