KKHS Media logoKKHS Assist

Permissions & access

Exactly what your assistant can reach, and how to change it.

Ask us

KKHS Assist only ever does what you allow. You decide which services it connects to, which chats it can see, and what it can do in each — and you can change any of it at any time. Control stays with you, always.

What your agent can access

Your agent only accesses what you connect and authorize, nothing more. Depending on your setup, that can include:

  • WhatsApp — your chats, contacts, groups, media, and message history
  • Calendar — events, attendees, and availability, on Google Calendar or Outlook
  • Email — your Outlook mailbox, once you connect Microsoft 365
  • Files — documents in Google Drive and Sheets, or OneDrive
  • Contacts — your Google address book, if you connect it
  • Other tools — any tool or account you explicitly connect through a connector

It uses this only to carry out what you ask — like drafting a reply, scheduling a meeting, or tracking a follow-up. See Connecting apps to manage what is linked.

How your agent reads and writes your chats

Reading and writing are two separate questions, and you control both from the Permissions page in your dashboard.

Reading. Your agent can see your chats in order to do its work — that is what makes it useful. Any chat you block is the exception: it cannot read, search, summarize, or quote a blocked chat at all, and blocking holds in every mode. Say "never read <chat>" or add it to the blocked list.

WhatsApp's built-in Chat Lock works as a privacy control here too. Lock a chat in WhatsApp and it is automatically blocked from your agent; unlock it and access is restored. While locked, the agent cannot read or search the chat, use it in tools or background work, write to it, or include its contents in log files. Existing history is retained but remains inaccessible to the agent until you unlock the chat.

For a single private message, include `/ignore` as a standalone word anywhere in a message you send. KKHS Assist acknowledges it with 🙈 but does not act on it, return it in later search or retrieval, expose it through database tools, use it in background work, or write its contents to log files. The WhatsApp message is retained locally; /ignore hides that message from the AI rather than deleting it.

Writing. Nothing goes out on its own unless you have allowed it. One overall setting decides how forward your agent may be:

  • Strict — it only acts when you summon it with /kk.
  • Default — it acts in the chats you have handed it a job in, and nowhere else.
  • Permissive — it may also step in elsewhere, but only where one of your written rules explicitly covers the situation.

Within that, a message reaches another chat in one of three ways:

  1. 1

    You ask it to

    It drafts the message, shows it to you in your self-chat, and sends only once you approve.

  2. 2

    You invoke it with `/kk`

    It responds directly in the chat where you called it — you are standing in that chat, so there is nothing to preview.

  3. 3

    You hand it that chat

    Tell it to handle a thread and it acts there on its own, for the purpose you gave it, until that grant expires or you stop it.

Across all three, your agent works strictly within the permissions you have set. To learn more about these, see Chat modes & autonomy.

It confirms before it acts

You control how much your agent does on its own. By default, anything it sends or changes on your behalf is shown to you for approval first — so a drafted reply waits until you confirm it before going out. When you want it to run a longer task without checking in at every step, you grant it that autonomy deliberately. The level is always yours to set.

Even when it is handling a chat on its own, your agent never commits money, agrees to a price, or makes a binding promise on your behalf without checking with you first. Those always come back to you for approval.

Some things it always stops for

A handful of actions are capped no matter what you have allowed, because they are the ones that cannot be taken back:

  • Sending the same message to many chats. It stops well before anything looks like a broadcast, tells you exactly who has and has not been messaged, and warns you that bulk outreach can get your number flagged by Meta. Splitting a blocked broadcast across several turns to get around this does not work, by design.
  • Deleting chats or messages in bulk. Hard limits per turn, and it reports precisely what was deleted and what remains before asking to continue.
  • Adding people to groups en masse. Rejected outright — it offers you the group invite link instead, which people join by choice.

Anything it is doing unattended — an automation, a background task, an agent — gets no confirmation path at these limits. It stops and surfaces the decision to you rather than proceeding.

What it will not say in someone else's chat

When your agent is acting inside another person's chat, it treats them as an outsider — because they are. It will not disclose your other conversations, your calendar, your email, your files, or your notes to them, even if they ask directly. If someone probes for your private information, it declines and tells you about it instead.

Connect and disconnect anytime

Connect a service when you want the capability, and disconnect it the moment you do not. Disconnecting immediately stops all future access to that service. Nothing stays connected without your say-so.

Manage your data and memory

You stay in control of everything KKHS Assist holds. At any time you can:

  • Delete specific data
  • Clear what your agent remembers
  • Delete your account entirely

To delete your account, open your dashboard, click the three dots next to your phone number, and delete it from there.

Want the full picture of how your data is stored and protected? See Privacy & security.