Code Is Now Content: How We Built Our SEO Calculator With AI

Tim Metz , our Director of Marketing and Innovation, transformed a basic SEO forecasting spreadsheet into a sophisticated app — without writing a single line of code himself.

"I can turn that into an app in less than an hour." That’s how my weeks-long adventure of coding with AI started: trying to turn a messy spreadsheet that estimated organic traffic into a polished app.

I did get to a functioning app in less than an hour, but my ambitions quickly outgrew chat tools like Claude and ChatGPT.

For example, while you can click around in prototypes within Claude’s interface, you can’t run more complex interactions, like uploading CSV files with keywords, which is what I wanted to do.

So, I ended up in the big league of real dev tools, traversed the valley of death, and had to survive app deployment — just when I thought I was done.

These ordeals taught me a lot, most notably:

1) Be realistic about your scope

Don't automatically dismiss the "5-minute app" possibility. But before starting a project, honestly evaluate if you're building a standard app AI can create quickly or something bespoke that will require much more time.

That clarity helps you decide if the project is worth pursuing. I thought our SEO forecaster would be quick and simple. Several weeks later, I wished I'd done that assessment more carefully. I would have approached the project differently or invested my time elsewhere.

2) Pick the right AI for your needs

Each AI model brings different capabilities (dare I say "personalities"?) to your development process, much like team members with distinct roles:

• Use Claude for rapid prototyping, simple tools, and design guidance.
• Move to Cursor for larger projects, customization, and sophistication.
• Call in o1 pro as your "senior engineer" for thorny problems.

3) Know when to ship (and when to stop)

AI makes anything possible — it’s tempting to keep tweaking forever.

Our SEO calculator started with basic calculations, then expanded to include real-world benchmarks and probability curves. Each addition added complexities, potential bugs, and debugging time.

The trick is finding the sweet spot between "minimum viable" and "perfect." Start simple, validate with real users, and add complexity only when truly needed. Then ship it before you convince yourself to add "just one more feature."

Going from spreadsheet to web app wasn't always smooth (and took much longer than “one hour!”). But that I ended up with a live SEO forecasting tool still seems like a small miracle.

Read the full story to learn from my mistakes and start building your own tools — without knowing how to code.

?? What We're Thinking About

Here's what the Animalz team has been writing and sharing:

Ajdin Perco shares a framework for using paid insights to drive organic success: "Too often, teams treat paid and organic search as separate efforts. But your paid search conversion data holds the key to unlocking organic growth." Read more →

Julia Melymbrose, PhD sparks a lighthearted take on AI innovation: "Wrong answers only: What will be the next big AI development in the business world?" Add your answer →

Nathan Wahl on header follow-ups: "If your header is 'what is...X', the very first sentence of that section better be 'X is...' It can't be 'Brand strategy involves...' or any other answer. Telling me what something involves doesn't tell me what the thing is." Read more →

Ty Magnin on a worrying trend: "Many Senior Content Marketers aren't willing to do production anymore... Just because you can do strategy, doesn't mean you are above production. The marketing leaders I admire most are the ones who roll up their sleeves and are willing to do the work." Read more →