Connecting your assistant
Connect Claude or ChatGPT to Protocol — two ways, depending on your app — plus managing and revoking the agent keys that grant access.
Basic Connecting takes a couple of minutes and you only do it once per app. There are two ways in, and which one you use depends on the AI app you have.
Two ways to connect
| Your app | How it connects | Best for |
|---|---|---|
| Claude or ChatGPT (web & mobile) | Connect button — you authorise Protocol once, like connecting Google Drive | most coaches — no setup, works on your phone |
| Claude Desktop, Claude Code, Cursor (developer apps) | paste an agent key into the app’s connection settings | power users already living in those tools |
Both end up in the same place: your assistant can now act on your Protocol account. The only difference is how you hand it the keys.
Option A — Connect (Claude / ChatGPT)
In your AI app’s connectors or integrations settings, find Protocol and choose Connect. You’ll be sent to Protocol to sign in and authorise — confirm, and you’re done. This is the same one-tap flow you’ve used to connect a calendar or a drive to other apps.
Option B — Agent key (developer apps)
For apps that ask for a key instead of a Connect button:
Copy it once. For your security, Protocol shows the full key only at the moment you create it. If you lose it, you don’t recover it — you create a new one and revoke the old. Treat a key like a password: it acts as you.
The one thing to read before you connect
The first time you connect, Protocol shows a short notice and asks you to confirm it. The important line:
Connecting an assistant sends the Protocol data it works with — including your clients’ information — to your AI provider (Anthropic for Claude, OpenAI for ChatGPT) so it can answer. That’s the trade for using your own AI. You’re responsible for that choice on your clients’ behalf, the same way you are for any tool you bring to your coaching.
This isn’t fine print to skim past — it’s the heart of how the feature works. Your assistant can only help by reading the relevant data, and reading it means it’s processed by the AI you chose. Nothing new becomes visible that you couldn’t already see; the new part is where it’s processed. More on exactly what’s shared, and how to limit it, in Data, privacy & revoking.
Your first message
Once connected, just talk to it. A good first prompt to prove it’s working:
Managing & revoking access
Everything you’ve connected lives under Account & settings → AI agent:
- See what’s connected — each app, when it last acted, and what it’s allowed to do.
- Revoke instantly — remove a key or disconnect an app and it stops working immediately. Do this the moment a device is lost or you stop using an app.
- Name your keys — “Claude — laptop,” “ChatGPT — phone” — so you know what you’re revoking.
Connecting is reversible and safe to try. Start with a key, ask it to read a few things, and revoke if it’s not for you. Nothing is changed in your account until you approve an action — see Approvals & safety.
Next: the headline use — Building & editing programs →