Built with Claude.

A portfolio that proves the point.

I didn't set out to make a case study about AI. I set out to make a portfolio, one that showed my work honestly, felt like me, and looked like something I'd be proud to send to a design director at a company I actually wanted to work at.

The decision to use Claude as my primary design tool was practical before it was strategic. I had a clear vision, real constraints, and no time to rebuild everything from scratch in Figma. Claude Design had just launched, weeks old, still finding its footing. I decided to see how far I could push it.

What I didn't expect was how much the process itself would become worth documenting.

I was the designer. Claude was the tool.

That distinction mattered from day one, and I had to enforce it constantly.

The direction was mine from the start. Quiet luxury editorial. The Pantone 2026 Color of the Year as the background. A deep slate blue as the only accent. Cormorant Garamond for headlines. The structure, the pages, the case studies, all of it came from my previous portfolio and my own thinking about what I wanted to say.

Claude's first attempt was competent and completely generic. A terracotta palette. Safe font choices. A layout that could have belonged to anyone. I pushed back and kept pushing through multiple rounds on the color palette, typography, and hero layout until the visual language matched what I had in my head.

Six years designing enterprise products gave me more than design skills. It gave me fluency in front-end thinking. I can read HTML and CSS, understand what z-index means, and spot when a border-radius is wrong before I even open the browser. That technical literacy changed the quality of my prompts entirely. Instead of saying "the photo doesn't look right," I could say "the object-position needs to shift to center 10% and the container needs overflow: hidden." Faster iterations, fewer misunderstandings, better results.

I also thought carefully about responsive design throughout the process. Every layout decision was tested across breakpoints, not just on desktop. That systems thinking, knowing how components behave at different sizes and how decisions compound, came directly from years of designing for enterprise platforms where consistency across contexts is non-negotiable.

The first drafts of my case studies were full of fabrications: invented metrics, quotes from colleagues that never happened, wrong place names, real employee names in dashboard screenshots. Catching and correcting those details required going back to my original work, my CV, my actual memory. The AI made it faster to generate. I made it true.

Getting my portrait photo right took over ten separate prompts. The goal was clear: editorial magazine treatment, photo bleeding from the nav, arch-shaped bottom, headline overlapping from the left. Claude understood the concept and kept defaulting to simpler solutions. Each time I pushed back with a reference image or a specific CSS correction. The gap between "Claude understood what I wanted" and "Claude produced what I wanted" was where all the real design work happened.

From prompt to judgment.

The most useful mental model I developed: Claude handles execution, I handle judgment.

Execution, writing CSS for a two-column grid, applying color values across eight HTML files, generating layout variations, Claude is fast and tireless at all of it. I stopped thinking of that as "AI doing my job" and started thinking of it as having a capable engineer who works at the speed of thought.

Judgment is everything else. Does this feel like me? Is this true? Is this the right word? Does this case study sound like something I actually believe, or does it sound like something a designer would post on LinkedIn?

Those questions cannot be prompted away. They required reading every line, pushing back on every fabricated detail, and making decisions that only I could make, because they were about my work, my story, my taste.

A full portfolio. 10 active days.

lilianalovo.com is live. It reflects the design direction I had from the beginning: quiet, editorial, human. The case studies are accurate. The copy is in my voice. The portrait took ten iterations and I'm glad I pushed for all of them.

The output is only as good as the judgment you bring to it. Claude made me faster. It didn't make me a better designer, that part was still mine. What it did was remove the friction between thinking something and seeing it on screen, which meant I could spend more time on the decisions that actually mattered.

The designers who will thrive with these tools are not the ones who prompt the best. They are the ones who can tell the difference between a good result and a convincing one.

The AI was the brush. I was still the painter.

My background as a product designer, understanding systems, front-end constraints, and how decisions compound, made me a better collaborator with Claude than I would have been without it. The technical literacy I built designing enterprise products translated directly into better prompts, faster corrections, and a clearer sense of when to push and when to accept.

Building this portfolio in 10 active days sharpened my instincts in ways I didn't expect. Every decision was mine: the color, the copy, the layout, the responsive behavior. There was no brief to hide behind and no stakeholder to defer to. That kind of ownership clarifies what you actually believe about design.

Claude Design had just launched when I started this project. It was rough in places, limited in others, and I spent real time steering it away from its defaults toward something that felt genuinely mine. What it produced with that guidance exceeded what I could have built alone in the same time.

That is not the ceiling. That is the starting point. Claude Design proved to be a genuinely useful tool for designers to iterate fast and get real results. This is just the beginning of how far designers and AI can go together, and I am glad I was building something real when this era began.