The prompt is the product

TLDR: Don’t ask AI to do the thing directly. Ask it to interview you first — what are your constraints, what have you not thought of, what would you recommend? Collect those answers into a brief. Use that brief as your real prompt. This works for anything: websites, business plans, marketing campaigns, internal tools, hiring processes. The example below is a website, but the method is universal. A 350-word brain dump became a 1,200-word spec, and the result wasn’t even in the same category.

You’ve got an idea for a website. You open Claude or ChatGPT and type something like:

“I’m starting a surf lesson business in Portugal. Can you build me a website?”

And the AI will do it. It’ll give you a homepage, maybe a contact section, some copy about how your services are “tailored to your needs.” It works. Technically.

But it’s thin. It’s missing things you didn’t know to ask for — SEO tags, legal pages, a contact strategy, cookie consent, schema markup. You never mentioned them, and the AI didn’t want to bother you with questions.

This isn’t a website problem. It’s a prompting problem. Ask AI to “write me a marketing plan” and you’ll get five generic bullet points. Ask it to “draft an employee handbook” and you’ll get boilerplate. Ask it to “plan my product launch” and you’ll get a timeline that could apply to literally any product. The pattern is always the same: vague input, vague output.

The quality of what you get out is almost entirely determined by the quality of what you put in. But to write a detailed prompt, you need to know what details matter. If you already knew that, you wouldn’t need the AI’s help. It’s like walking into an architect’s office and saying “build me a house” — you’ll get a house, but not the one you actually wanted.

So what do you do?

Make the AI interview you first

Instead of asking the AI to build the thing directly, you ask it to help you figure out what to ask for. Thinking partner first, builder second.

I do this with clients all the time. Before I touch any automation, I spend the first few sessions just asking questions. What breaks when you’re on vacation? Where do you lose money to slowness? The answers shape everything that comes after. You can do the same thing with AI — for free.

Say you’ve got a rough idea for a corporate surf retreat business called “Salt & Suit.” If you dump all of it into an AI and say “build me a website,” you’ll get one page, some blue colors, and generic copy. No SEO strategy, no legal compliance, no plan for how anyone will find it.

But if you say this instead:

I have a business idea and I want you to eventually build me a website. But not yet. First, help me think through what the website actually needs. Here’s my rough idea: [your brain dump]. Ask me the questions I haven’t thought of. Tell me if I’m missing something obvious. As we talk, build up a detailed brief that captures all our decisions. That brief becomes the build prompt later.

Now the AI starts asking things like:

Where will you host this? (It might suggest Astro + Tailwind for static sites with good SEO.)
How will people contact you? A form? A Calendly link? Each has trade-offs.
What about legal stuff — privacy policy, GDPR cookie consent?
Will the site be English only, or Portuguese too?
Do you have photos? If not, where will the visuals come from?

You answer these. After three or four rounds, you’ve got a document that’s no longer a vague idea — it’s a proper brief. And that brief is your prompt.

The template

If you want to try this yourself, adapt this to whatever you’re building:

I have an idea for [what you’re building] and I eventually want you to help me build it. But not yet.

First, I want you to be my thinking partner. Here’s my rough idea: [your brain dump — be as messy as you want].

Before we build anything:

Ask me questions I haven’t thought of. Explain why each one matters, and suggest what you’d recommend if I’m not sure.

If something in my plan is a bad idea, tell me directly.

Think about this from the end user’s perspective. What would they expect? What would make them trust this?

After each round of questions, update a running brief that captures all our decisions. This brief becomes the build prompt.

Ask me questions in small batches so I don’t get overwhelmed. Don’t build anything yet.

You go back and forth a few times. The brief grows. When you’re done, you’ve got a prompt that’s five or ten times more detailed than what you started with — not because you spent weeks researching web development, but because you had a conversation.

The worked example: before and after

Here’s the full process from the surf retreat scenario. The rough idea on day one, then what came out the other end.

The starting prompt (what’s in your head)

Read Elena's starting prompt (~350 words)

I’m starting a corporate surf retreat business in Portugal and I need a website. Can you build it for me please? My name is Elena. I’m originally from Lisbon but I spent 15 years in London working in finance. I picked up surfing on holidays in the Algarve and while I really love the sport and the culture around it, I found it really frustrating to try surfing in popular spots like Bali, Hawaii, or Australia because of the crowds and the prices. You show up at a beach and it’s packed. The surf schools charge crazy money. Everything feels like a tourist trap. It’s exhausting.

I moved back to Portugal and started surfing regularly along the coast near Ericeira, which is a world surfing reserve about 45 minutes north of Lisbon. The waves are incredible, the beaches aren’t overcrowded, the food is amazing, accommodation is cheap, and the whole vibe is just relaxed and real. It’s one of the best kept secrets in European surfing.

So my idea is this: if a company from anywhere in Europe wanted to do a corporate team-building retreat that’s actually fun and not just another boring offsite, they could come to Portugal and I would handle everything. I’d book the surf school, organize the accommodation, arrange airport transfers, plan the meals, and be their go-to person throughout the whole trip. I’ve got this mix of corporate polish from my London years and laid-back surf energy that I think works well. I’d be like their best friend throughout the whole experience.

My clients would come during spring, summer, or early autumn, have an amazing time, and fly home. Flights from most European cities are short and cheap. It’s a no-brainer.

I have a business partner named Marco Ferreira. He’s mentioned on one of the pages. He’s the surf guy — a certified ISA surf instructor who’s been teaching for 12 years. He knows every break along the coast and he’s the one who runs the actual surf sessions. I handle the logistics, the client relationships, and the corporate side.

The website is going to be called Salt & Suit. It’s a play on the idea that we’re taking people out of their suits and into the salt water. Corporate meets coast. I want the website to feel a bit playful and irreverent — like, we take the surfing seriously but we don’t take ourselves too seriously. But it still needs to feel professional enough that an HR director or a team lead would trust us with their offsite budget.

Good energy, clear value proposition, zero implementation detail.

The refined prompt (what came out the other end)

Read Elena's refined prompt (~1,200 words)

I’m starting a corporate surf retreat business in Portugal and I need a website. Can you build it for me please? My name is Elena. I’m originally from Lisbon but I spent 15 years in London working in finance. I picked up surfing on holidays in the Algarve and while I really love the sport and the culture around it, I found it really frustrating to try surfing in popular spots like Bali, Hawaii, or Australia because of the crowds and the prices. You show up at a beach and it’s packed. The surf schools charge crazy money. Everything feels like a tourist trap. It’s exhausting.

I moved back to Portugal and started surfing regularly along the coast near Ericeira, which is a world surfing reserve about 45 minutes north of Lisbon. The waves are incredible, the beaches aren’t overcrowded, the food is amazing, accommodation is cheap, and the whole vibe is just relaxed and real. It’s one of the best kept secrets in European surfing.

So my idea is this: if a company from anywhere in Europe wanted to do a corporate team-building retreat that’s actually fun and not just another boring offsite, they could come to Portugal and I would handle everything. I’d book the surf school, organize the accommodation, arrange airport transfers, plan the meals, and be their go-to person throughout the whole trip. I’ve got this mix of corporate polish from my London years and laid-back surf energy that I think works well. I’d be like their best friend throughout the whole experience.

My clients would come during spring, summer, or early autumn, have an amazing time, and fly home. Flights from most European cities are short and cheap. It’s a no-brainer.

I have a business partner named Marco Ferreira. He’s mentioned on one of the pages. He’s the surf guy — a certified ISA surf instructor who’s been teaching for 12 years. He knows every break along the coast and he’s the one who runs the actual surf sessions. I handle the logistics, the client relationships, and the corporate side.

The website is going to be called Salt & Suit. It’s a play on the idea that we’re taking people out of their suits and into the salt water. Corporate meets coast. I want the website to feel a bit playful and irreverent — like, we take the surfing seriously but we don’t take ourselves too seriously. But it still needs to feel professional enough that an HR director or a team lead would trust us with their offsite budget.

The website needs photos — everyone wants to see the beaches and the surf. However, I don’t have professional photos yet. Find some relevant photos of the Ericeira coastline and the surf scene there and use them as placeholders on my website.

You’ll have to not only create this website, but also lead me through promoting it from the “cold start”, meaning that I currently have just the domain name (saltandsuit.com), the vague idea about what I want to do, and not that much else. I probably need something like a go-to-market strategy or something?

The website is to be hosted on Cloudflare Pages, so probably needs to be done in Astro + Tailwind, and be mostly static for SEO purposes. If you need a database, use Cloudflare D1, i.e. SQLite3.

The website should have all the components needed for having great indexability and SEO, including but not limited to sitemap.xml, robots.txt, all the canonical tags, OpenGraph tags, JSON-LD annotations, favicon and such. Think a bit about what components are needed and suggest what should I add.

We should try to make the website self-contained, i.e. it should not load any external resources, unless the external resource would significantly increase either the marketing value of the website or make it more useful to the user. One notable exception to this previous self-containment rule is that I’m going to use PostHog for tracking both visitors and recording their sessions.

If I’m proposing something that would be against the best interests of this business either now or in the future, please tell me so right away.

Think out of the box about how to make the website more convenient for the visitors and get more leads. Should I have a 30 minute call on Calendly? Post my phone number? Have a form to fill out? What’s the best way to get into some sort of a contact with a warm lead for a website for a business such as mine?

I suppose the website should have a cookie consent banner but it shouldn’t be too big or too annoying.

There should be placeholders for photos of me (Elena) and my instructor (Marco). I will provide photos later.

The website should be responsive, i.e. look good on desktop, mobile, tablet etc. Also, don’t make the font too small.

Under no circumstances should the text on the website look AI generated.

In the website, convince the visitors that I will handhold them personally throughout the whole process, i.e. if need be, I will book the flight tickets (or help them in booking them), get the transportation, hotel bookings, everything. Also mention that it’s not only me who’s working on this, I have a small team, so that they don’t ever think that I might be overwhelmed by their business/trip — no, there’s always going to be someone taking care of them at all times.

Add terms and conditions and privacy pages and in both mention that this is hosted in Portugal, which is an EU country among other things.

Add a frequently asked questions page and appropriate sections all over the website and put something sensible in them.

I will also need a logo for this website so draw a logo using scalable vector graphics. The logo should combine a surfboard and a necktie in some clever way. Keep the brand colors in mind — ocean blues, sandy neutrals, and maybe a pop of coral.

Don’t hesitate to link to external resources such as YouTube videos or websites and when linking don’t add the noreferrer tag.

The website should have both the light and the dark mode and switch automatically based on the user’s setting, with an ability to toggle between the two modes.

Don’t just fill the website with bland text. Add SVG illustrations for buttons, actions, concepts, and anything else that makes sense.

When creating content for the website, we should always take into account that we want ChatGPT and other AI bots to refer to the website when people ask questions about corporate retreats in Portugal. Research strategies about how to format and present content to make it more quotable by AI chatbots.

When creating the website, keep Google’s topical maps in mind. Research what topical maps are, plan on how they apply to this website, and use that when organizing the content.

The website will eventually have both English and Portuguese versions. For the time being, create only the English version, but research the best way to implement the Portuguese version later for SEO purposes, and add a disabled Portuguese language switch somewhere.

Leave placeholders for social media links — Facebook, Instagram, LinkedIn, and any other appropriate ones. I haven’t set them up yet.

Research what Google E-E-A-T is and design the website structure according to that.

What sets of pages should I have for SEO purposes? A SaaS would have “industries” and “case studies” and “use cases”, but what sets of pages could a corporate surf retreat website have? Figure it out and make a plan.

If I’m suggesting something stupid, don’t hesitate to let me know. Always keep my current state of things in mind — I’m just getting started with the website and I want to make it more popular.

Think whether or not I’m missing something, and if I am, propose those ideas to me.

MAKE A PLAN WHAT YOU WILL DO.

350 words became 1,200. The extra words aren’t fluff — they’re decisions about hosting, SEO, legal pages, analytics, contact strategy, dark mode, content structure, multilingual support, E-E-A-T, and topical maps. None of which Elena would’ve thought to mention. All of which came out of the conversation.

Same AI. Same person. Wildly different output.

The prompt is the product

People treat prompts as throwaway inputs — type something, get a result, move on. But for anything that’s not trivial, the prompt is the product. It’s the spec. The blueprint. You wouldn’t build a house from a napkin sketch.

The example above is a website, but I use this exact method for everything. Designing an automation workflow for an accounting firm? Interview first, build second. Planning a content strategy? Same thing. Migrating a client’s data pipeline? You’d better believe we’re spending the first hour on questions, not code. The two-step process works wherever the gap between “what you know to ask for” and “what you actually need” is wide — which is most places.

I spend the first chunk of every client engagement just asking questions and building the brief before anyone touches a keyboard. But you can get 80% of that value on your own, for free, by running this two-step process with any AI chatbot. The AI won’t know your industry as well as a consultant would, but it’ll catch the 30 things you forgot to think about. That’s usually enough.