Security and your data

Every agent runs on its own isolated server. It sees your data and nobody else's, and it can only reach systems you have connected yourself.

Where does my data live?

On the agent's own machine — its memory, its files, its working directory. Agents of different customers do not share a server, so one customer's data is never in another's reach.

What can the agent touch?

Exactly what you gave it: the channels you connected, the documents you shared with its address, the accounts whose access you handed over. Nothing else exists for it.

How do I take access back?

The same way you gave it. Unshare the folder in Google, remove the agent from the chat, revoke the key in the service. It takes effect immediately — there is nothing to ask us for.

How are secrets handled?

Passwords, tokens and login codes are never taken in chat. The agent issues a one-time secure page and the secret goes straight into its encrypted storage. If someone asks you to paste a password into a conversation, that is wrong — ask for the secure link instead.

What about payment data?

Card details are entered on the bank's secure page. We never see or store card numbers.

Can the agent act without me?

It acts within the job you gave it. Anything irreversible or outward-facing — writing to a client, publishing, deleting — is worth putting under an explicit rule: "ask me first". Tell it once and it holds.