Free resource · 01

Turn customer questions into useful content ideas

Start with a question someone has already asked you.

The Content Idea Engine is an AI workflow for choosing which questions deserve an answer, what you can add, and what evidence supports it. Give it your audience, offer and source material, then review the ideas before writing.

Claude ChatGPT Manus Needs web search
What you get

Three things, every week

01
Three ready-to-make ideas
Each with the signal, the angle, the proof, the hook, and the one offer it points to.
02
A buyer-language log
5–10 exact quotes, ready to drop into a hook or caption.
03
A parking lot
What was loud but not yours to say this week — and why.
The skill prompt

Use the Content Idea Engine prompt

Fill in the config block once at the top. Everything after that runs the same way every week.

Use customer material you have permission to use, and remove private details. When the model finds a public question or quote, open its source link yourself. Treat its scores as a way to organize your review, not proof that an idea will perform.

Quick version

In a hurry? Paste this instead

Same logic, condensed to one paragraph. Swap in your own details before sending.

quick-prompt.txt
You're my weekly content research assistant for [FOUNDER/COMPANY], selling [OFFER] to [ICP]. Use web search to find 10-15 real posts, comments, or questions from people who match my ICP - real links only, no invented sources. For each, note the exact quote (not paraphrased) and score it 0-5 on: fits my ICP, lets me say something nobody else is saying, I have real proof for it, gives me a usable quote, connects to a buying trigger or offer, and the source is solid and recent. Only keep signals scoring 22+ out of 30 - anything with huge engagement but a low "can I own this" score goes on a parking list instead. Turn my top 3 into ready-to-make ideas: the signal + link, the angle nobody else is naming, my real proof for it (or say I don't have proof yet), a one-line hook in my voice, and which offer it points to. Add 5-10 verbatim buyer quotes and the parking list. No hype words, one offer per idea, only claim what the source actually shows.
Setup

How to run it

01
Fill in the config block
Your business, offer ladder, ICP, triggers, voice rules, and 2-3 real proof assets. Do this once — it decides whether every week after this is sharp or generic.
02
Save it somewhere reusable
In Claude: a Project's custom instructions or a Skill. In ChatGPT: a Custom GPT or saved prompt. In Manus: a recurring task.
03
Make sure web search is on
Without it, the model will invent plausible-sounding "signals" with fake sources. Confirm browsing is enabled before your first run.
04
Run it once a week
Same day, same time. Paste in last week's numbers if you have them — it'll use them for the one-test-to-try suggestion.
Illustrative example — not a real result

What a run actually looks like

A fictional founder, so you can see the shape of the output before you run your own.

ConfigJordan — scheduling app for independent personal trainers. Offer ladder: free booking template → app subscription → done-for-you onboarding.
Signal found"I lost like $400 this month just from people not showing up and me not charging a fee because I felt bad."
Score27/30 — direct ICP, real trigger (no-show revenue loss), maps straight to the app's cancellation-fee feature.
AngleEveryone talks about "no-show policies." Nobody's talking about why trainers don't enforce the ones they already have — it's not a policy problem, it's an awkward-conversation problem.
Hook"Your cancellation policy isn't the problem. Enforcing it to someone's face is."
Points toFree booking template (the awkward part is automated away)
Expected output

Three things land in your doc

3 ready-to-make ideas

Signal, angle, proof, hook, and the one offer each points to.

Buyer-language log

5–10 verbatim quotes, ready for a hook or caption.

Parking lot

What was loud but not yours to say — and why.

Turn it into content

From idea to a finished piece

01
Film the hook alone
If it doesn't work standing by itself, the idea isn't sharp enough yet — go back to the angle, not the delivery.
02
Use the exact quote
In the caption or the opening line. Recognition beats cleverness.
03
One idea per piece
Don't cram all three ready-to-make ideas into a single post.
04
Show the proof
A number, a screenshot, or a specific story beats an adjective.
05
End on the one offer
The one the idea already pointed to. Don't swap in a different CTA at the last second.
The ideas were never the hard part. Having a system that hands them to you is. — Definitely Human
Next step

Keep building in the Society

Join Martin's AI Marketing Society for free resources and live sessions. You can also try the prompt above without an account.

Join the free Society

Build the next part

Prepare the facts with an AI context document, document your AI brand voice, then take the idea through an AI marketing workflow with evidence checks and human review.