You run thisWritten for ChatGPT, Claude or Gemini
Find out what my AI can already reach, and what I'm not using
Founder, Automation Squad
Most people use a tool with six live connectors as though it were a blank chatbot, because nothing in the interface ever tells you what it can reach. Asking the model to audit itself surfaces the gap in about thirty seconds, and section 4 is where it earns its place — it turns an abstract capability list into five jobs you could start today.
The prompt
Before you answer, take stock of yourself. List everything you can currently do on my behalf. Break it into: 1. WHAT YOU CAN READ — memory about me, past conversations, files I've uploaded, and any connected accounts (email, calendar, drive, notes, CRM, code). Name each one specifically. If you're connected to something but I've never asked you to use it, say so — that's the point of this exercise. 2. WHAT YOU CAN DO, not just read — send, create, schedule, edit, run code, search the live web, generate images. Be precise about the difference between "I can look at your calendar" and "I can put things on it." 3. WHAT YOU CANNOT DO that people commonly assume you can. I'd rather be disappointed now than halfway through something that matters. 4. THE FIVE THINGS I'M PROBABLY NOT ASKING FOR. Based on what you're actually connected to, name five useful jobs I could hand you today that most people in my position never think to. For each: one line on the job, and the first sentence I'd type to start it. Rules: don't list capabilities in the abstract — only what's live for me, in this account, right now. If a connection exists but is broken or unauthorized, flag it. Don't pad section 4 with generic ideas like "summarize documents"; I want things that only make sense because of what you're specifically connected to.
Copy it, paste it, run it. Nothing here is gated.
More for the same job
Written for ChatGPT, Claude or Gemini as of August 2026. Models change — if this stops working the way it should, that is worth telling us about.
