AI can generate a website. But it can't always communicate a business's value.
Recently, I worked with a client who already had an AI-generated website. It looked decent at first glance, but it wasn't conveying the quality of their service or guiding visitors toward the right action.
Instead of starting from scratch, we focused on what really matters:
• Clear information hierarchy
• Conversion-focused user experience
• Premium visual consistency
• Responsive design across devices
• Scalable Webflow structure
• Performance and SEO best practices
AI is becoming an incredible tool, and I use it in my own workflow every day.
But great websites are still built by understanding people, business goals, and user behavior. Not just generating layouts.
That's where thoughtful design and development make the difference.
Today’s project: second-level communication for a pharmacy I’ve been working with as part of an ongoing brand redesign.
I connected Claude to Affinity through its new scripting capabilities, defined the artboards and dimensions, prepared the content in a structured CSV, and set up a workflow to generate and organise all the assets with consistent naming.
The exciting part for me is that this wasn’t just about using AI to generate something. I designed the workflow myself: structuring the data, defining the visual requirements, and figuring out how to turn a repetitive production task into a streamlined system.
And then… I watched a little robot open Affinity, create everything, organise the files and name every artboard perfectly in about 10 minutes.
I have to admit, watching it happen was slightly surreal. And very, very satisfying. 😍
AI can build a page quickly. Keeping it recognizably yours is the harder part.
Vercel is testing a simple idea: give AI clear design guidance before it starts—not just colors and fonts, but the decisions that make a brand feel consistent.
The bigger lesson applies to any business: AI works better when your taste is documented instead of trapped in someone’s head.
A clear creative guide turns “make something nice” into repeatable decisions—and makes faster work feel less generic.
If an AI had to represent your brand tomorrow, what rule would you teach it first?
Your website is no longer just being read by people.
AI search engines are reading it too and they understand your website in ways surprisingly similar to how a good UX designer evaluates it.
@Framer's latest AEO guide highlights a few things that matter:
1. Clarity beats cleverness - If a page jumps between ideas, uses vague language, or assumes too much context, AI systems have a harder time understanding what the page actually means.
2. Structure matters - Clear headings, sections, summaries, definitions, and FAQs help AI break content into usable chunks. That is essentially good information architecture.
3. Context > Keywords - AI search is not simply matching keywords. It is trying to understand relationships between ideas, anticipate follow-up questions, and determine whether a page provides enough context to answer them.
This changes how I think about AEO.
You don't need to "write for AI." You need to build websites that are genuinely easy to understand.
For humans first. And increasingly, for machines too.
That means website strategy, content architecture, UX, SEO, and AI discoverability are becoming much more connected.
The interesting part?
Good UX is starting to become good AI optimization.