Questions to Ask an AI That Knows Your Data (Better Than Any Viral Prompt)
Viral prompt lists give everyone the same answers. These are the questions I ask an AI connected to my real data: meetings, health, tasks, and market research.
You've seen the posts. "I talked to a growth strategist and put everything she asked me into Claude. Here are the six questions you should be asking." Honestly, they're not bad. But they're not always right, and they hand everyone the same six questions, which is exactly why they produce the same answers for everyone.
I screenshot those posts constantly. I just use them as reference for the kinds of things I could be asking, instead of running them word for word. The questions that actually change how I run my business all have one thing in common: they point the AI at data that's mine.
One setup note before the questions: all of these require connecting your AI to your own tools through MCP (Model Context Protocol, the standard plug that lets an AI read your other apps). The MCP starter guide covers that in 15 minutes. Once you're connected, steal these.
The leadership audit (ask it monthly)
Go through all of my meeting notes from the past month. How can I
improve my communication? Are there tasks where we dropped the ball?
Are we getting consistent feedback from clients, positive or negative?
How can I improve as a leader, and how can my team be doing better?
When my team is on calls and I'm not there, what am I missing?
That's close-to-real-time feedback on your own leadership, pulled from what actually happened in your meetings. Most people get that once a year in a review, if ever.
The health trends read
Go through my [wearable] data and my food log from the past month.
What trends are you seeing? Are certain meals, or meal times,
affecting my energy, my sleep, my workouts? What blind spots do I
have? Where can I be doing better?
Same move, personal side. I run this against my Oura ring and my meal log. The data was already sitting there. Nobody was reading it.
One thing I believe strongly here: AI plus a human expert beats either alone. I still work with a nutritionist. The AI does the logging and the pattern-spotting; she does the judgment. Then I feed her feedback back into my setup so it coaches me better between our check-ins. Use the AI to make your experts more useful, never to replace the judgment you hired them for.
The commitments check (ask it weekly)
Compare my meeting notes from the past two weeks against my task list.
What did I or my team commit to that never became a task? What's
overdue that someone is probably waiting on? List each one with where
it came from.
This is the question that catches the dropped balls while they're still catchable.
The market scout (ask it before you expand)
I'm considering expanding into [market]. Here's the brief and who our
customer is: [paste]. What's the area of opportunity? What are our
blind spots? What do we need to think about that we haven't? What's
the realistic revenue potential, and the profit potential? Cite your
sources for every claim.
For research like this I use a dedicated research agent (Manus or Perplexity) over a general chat tool, because they're built for it and they cite every source, so I'm not left wondering what was guessed.
The brain-dump sorter (ask it whenever you're overwhelmed)
Here's a brain dump of everything on my mind right now: [talk it all
out]. Sort it into four buckets: things I need to do now, things to
delegate to my team, things you can handle for me, and things to let
go of for now. For anything in the first bucket, suggest which day
this week it should happen.
Then let it actually take the third bucket. That's the difference between an AI that plans your work and one that does some of it.
The pattern behind all five
None of these came from a carousel, and every one of them works because it runs on data that's mine: my meetings, my health, my commitments, my market, my mess. Borrowed prompts run on the average of the internet, so they return the average of the internet. Borrow the thinking, then aim it at your own data.
The prompt was never the valuable part. Your context is.
FAQ
Do these work in ChatGPT or only Claude? The thinking works anywhere. The requirement is connection: your AI has to be able to read your notes, tasks, and data. I use Claude because its connector ecosystem fits my stack.
Aren't viral prompt lists useful at all? As idea references, genuinely yes. I save them. The mistake is running them verbatim and expecting output that sounds like you, when the prompt knows nothing about you.
What if I don't have much data connected yet? Start with one source. Meeting notes give the fastest payoff: even one month of them makes the leadership audit and the commitments check work.
Is it safe to give an AI my health data? Treat it like any sensitive data decision: know the provider's data policy, use accounts you control, and share the minimum that makes the question answerable. And keep a human expert in the loop for anything that matters.
