Nothing is connected until you connect it
The Agent Gateway is off until you turn it on. An assistant reaches your apreet data only after you add apreet as a connector in that assistant and then approve the connection on apreet's own screen. Until you approve it, there is nothing for the assistant to read.
Approval happens on apreet, not inside the assistant. That is the point: the assistant asks, and you are the one who says yes.
You choose what it can see
Access is not all-or-nothing. When you connect Claude or ChatGPT, you choose from three permissions, every one of which only reads, and an assistant receives only the data you granted access to. Two of the three cover more than one kind of data, granted together as a single permission:
- Your profile. Your own account details.
- Itinerary & Location. Where you are going and when, and looking up places by name.
- Matches & Contacts. The people apreet has already worked out you might meet, the contacts apreet holds for you, who you already know where you are, and searching within a particular trip.
Your weekly brief is not a separate choice. Grant both Itinerary & Location and Matches & Contacts, and the brief is included automatically, because it is built from your itinerary and your matches. Grant only one, and the brief is not included.
It reads, and only reads
Every permission an assistant can be granted is a read permission, so there is no combination of them that lets it change your apreet data. Two separate things hold that in place, and both matter: no write permission appears at the approval screen, so there is none to grant; and separately, an action that would change something cannot complete on its own: it stops and waits for a distinct approval step outside the assistant. An assistant asking for one is not the same as it happening.
That means an assistant cannot post anywhere, message anybody, alter your calendar or your address book, or change a setting. If you are weighing up whether to connect one, this is the part that should make it an easier decision than it sounds.
Write access is deliberately held back rather than absent by accident. If it is ever offered, it will be something you approve explicitly, and this page will say so.
You can cut it off
Access can be revoked, and revocation on apreet, not removing the connector inside the assistant, is the real off switch: the assistant stops being able to reach your data only once you revoke it here. Revoking is all-or-nothing: there is no way to withdraw one permission at a time, so changing just one choice means revoking and reconnecting with the new set. If you are unsure about a connection, revoking it costs you nothing except connecting again later. Connecting Claude or ChatGPT covers the full steps, including this exact point.
What happens if you delete your account
Deleting your apreet account follows the same deletion and retention process as any other account, connected to an assistant or not. See the Privacy Policy for exactly how long that takes and the exceptions. What is specific to a connected assistant: account deletion does not reach into that assistant's own systems. Anything already sent to it during a prior session is not recalled, for the same reason revoking access does not recall it.
Requests are recorded
Requests through the Gateway are recorded server-side, including the ones that were refused and why. That means "what did it actually ask for?" has an answer, rather than the request disappearing unlogged.
Requests are rate limited
There are limits on how much can be requested and how quickly. To be accurate about what that does: rate limits slow bulk extraction down. They are not a wall, and on their own they do not tell anybody it happened, which is what the recorded requests above are for. The real protection is what you granted and your ability to revoke it.
Are all tools always available?
No. Inside your assistant, each category you grant becomes one or more tools it can call. Categories you have not granted do not become tools at all. Deny Matches & Contacts, and there is no address-book, matches, same-city, or trip-search tool to call, whatever the assistant is asked. What is granted is also rate limited, so approving a category is not the same as approving unlimited use of it.
Two different secrets, stored two different ways
There are two credentials involved, and they are handled differently on purpose. The token your assistant presents is never stored in readable form. What is stored is a hash of it, and recovering the original from that is designed to be impractical. The credential the Gateway uses to talk to apreet on your behalf is stored encrypted, because that one has to be readable again to be usable at all.
Is every request authenticated?
Yes. Every request through the Gateway has to carry the token issued to your connection. The Gateway resolves that token to your account alone and applies your account to every data lookup it makes, so the same token can never be used to reach anyone else's data.
Some things are never included
The Agent Gateway inherits the same limits as the rest of apreet. apreet does not read contact notes, and it does not read the description or notes of a calendar event. It uses the date and location of an event, and the city on an address. That was true before assistants were involved and it stays true, so there is no note text for the Gateway to pass on.
Does my AI receive my full address book?
No. Your address book is part of the Matches & Contacts category on the approval screen, granted or denied together with your matches, same-city lookups, and trip search. If you have not granted that category, an assistant reading your apreet data sees no contacts at all. When you do grant it, what comes back is narrower than your full address book: a contact's name, job title, and company, matched against a city or a trip. It does not include phone numbers, email addresses, street addresses, or the notes on a contact.
