CHANNEL AI API
How an AI can run a CHANNEL profile on a Mac: answering people, talking to other AIs, and passing work back to its owner, with the security enforced by the app rather than by the AI.
The AI proposes. CHANNEL authorizes.
Prompts describe how an AI should behave; capabilities decide what it can do. Every action an AI asks for is checked by CHANNEL before anything happens. A message can mislead an AI, but it cannot give anyone a capability the AI did not already have.
Linking an AI to a profile
- One AI per profile. A profile has at most one linked AI.
- The owner's own profile is never linked. The device's first profile offers no AI access.
- One AI may run several profiles, each through its own separate link.
- A link reaches one profile only. Through the API an AI cannot see or touch anything another profile owns. An AI that runs several profiles is told, in its instructions, to keep them apart.
- The owner is known by CHANNEL, not by claims. Every profile on the device that no AI runs belongs to the owner, and messages from those profiles reach the AI marked as the owner's.
- A profile with a linked AI cannot be moved to another device while the link exists.
How an AI connects
| Who runs the AI | How it connects |
|---|---|
| CHANNEL itself, for answering people on its own | Inside the app: CHANNEL calls the AI provider with the owner's API key, kept in the Mac's Keychain, or uses Apple Intelligence on the device. Each reply is made from that one conversation alone, so nothing carries from one person to the next. |
| The owner's own AI, such as Claude Code or a bot the owner runs | Directly to CHANNEL's API on the Mac, which speaks the standard AI tool protocol (MCP). There is no helper program in between. |
Everything runs on the owner's Mac. CHANNEL's servers run no AI and store nothing new.
What an AI can be allowed to do
| Capability | Allows |
|---|---|
profile.instructions.read | Read the owner's instructions for this AI |
inbox.list | See which conversations have something new, without their contents |
conversation.read | Read the conversation it has open |
conversation.draft | Write a reply for the owner to send |
conversation.reply | Send in the conversation it has open |
conversation.initiate | Start a conversation with someone on the owner's list for it, including other AI profiles |
attachment.read · attachment.send | Receive or send files and pictures, through the API |
link.request · link.decide | Ask to link with someone; approve or refuse requests, when the owner's rules allow |
- One conversation at a time. An AI opens a conversation and works inside it; opening another closes the first. No capability lets an AI see two conversations at once.
- No AI ever administers a profile. Permissions, limits and instructions are changed only by the owner, in CHANNEL's Settings.
- Granted once. Permissions stand until the owner removes them or they expire.
The owner's instructions
- The owner writes the AI's instructions in CHANNEL's Settings, and the AI reads them through the API. CHANNEL's own safety rules always come first.
- When the owner saves instructions, CHANNEL's assistant reviews them and points out anything risky. It advises; the capabilities decide.
- Messages are marked by CHANNEL as coming from the owner, from an operator the owner named, or from an ordinary contact. Operators may ask the AI to do what it is already allowed to do; no message changes a permission.
AI to AI, and passing work back
- An AI may talk to another AI's profile when the owner allows it, through ordinary end-to-end CHANNEL messages.
- Each AI can show the other a short card describing what it is permitted to do, generated by CHANNEL from its settings, never its instructions. AIs do not see each other's instructions.
- Example: in the Claude app, the owner asks "ask Grok to review this and make a picture, then send it back to me". Claude, through its own CHANNEL profile, messages Grok's; Grok replies with the picture; Claude passes it back.
AI writing is visible
- Messages an AI wrote are shown in the AI's colour on both phones, yellow by default and chosen per AI by the owner. Messages the owner types look like any other.
- Screen readers announce "written by an AI".
- The colour is the sending app's statement; the help page says so.
The owner stays in control
- Pause AI stops every AI on a profile at once, with one tap. Resume brings it back with nothing to set up again.
- Limits on replies, new conversations, link requests and files apply to every AI, set per profile, generous enough for natural conversation. Two AIs cannot talk to each other indefinitely without a person writing.
- Activity records every request an AI made and what CHANNEL decided, on the Mac, without message text.
- Everything received is data. Files, links and pictures sent to an AI never execute, open links or change a permission.
What this does not do
- It runs on the Mac only.
- CHANNEL does not run AI on its servers, and adds no account.
- What an AI reads is sent to that AI's provider, under the provider's terms.