Designing What the Client Can See in Their Head but Cannot Explain
Our client was developing a new digital product with a strong sense of what it should feel like — "I want it to feel premium, but not corporate" — but very few concrete visual requirements. The first references they shared were completely different from one another: one minimal, one heavily animated, one from an unrelated industry. Copying those references would have produced a design the client technically approved but did not truly identify with. Instead, Envion built the client’s visual vocabulary together with them — architecture, fashion, editorial layouts, automotive interfaces, packaging, animation — using AI to explore directions in hours that previously took days. After several rounds, patterns appeared; that was the real brief. The final direction combined elements the client had never explicitly described together, and their response was: "Yes. That’s exactly what I had in mind."
The challenge
One of the most interesting parts of UI/UX design happens before Figma is opened. A client comes to you with an idea. They know what they like when they see it. They may have a competitor they admire, a screenshot from another industry, a particular feeling they want the product to create, or simply a sentence such as: "I want it to feel premium, but not corporate."
Our client was developing a new digital product and had a strong sense of what it should feel like, but very few concrete visual requirements. The first references they shared were completely different from one another. One was minimal. One was heavily animated. Another came from an unrelated industry.
If we had simply copied the visual characteristics of those references, we would have produced a design the client technically approved but did not truly identify with. So we approached the project differently.
Decision path
When a client sends a website and says "I like this," our next question is never simply "should we make yours similar?" We dig further. What exactly do you like? Is it the amount of whitespace, the movement, the typography, the confidence of the messaging, the photography, the simplicity, the darkness, the density, the feeling of exclusivity, the way information is revealed?
Quite often, the thing the client loves is not the thing they initially point to.
So we started collecting references together — not only competing products. We looked at architecture, fashion, editorial layouts, mobile apps, packaging, automotive interfaces, product photography, animation, typography, dashboards, and completely unrelated websites. This helped us create a shared visual language. Instead of asking the client to explain design terminology, we gave them things to react to: more like this, less like this, this feels too corporate, this feels too playful, this animation is right but the typography isn't. After several rounds, patterns started appearing. That was the real brief.
Envion contribution
AI has made this stage dramatically faster. We use it to explore directions that previously would have taken days to visualize: alternative hero concepts, interface composition ideas, different image styles, visual metaphors, illustration directions, unusual combinations of styles, copy and visual pairings, and animation concepts.
Instead of presenting the client with one polished direction after several days, we can explore a much wider range of possibilities early. The client reacts. We learn. AI generates another direction. We refine again.
The purpose is not to ask AI to design the product for us. It is to shorten the distance between what the client imagines and what the designer can show them. And AI needs direction too: "create a modern SaaS website" produces a modern SaaS website that looks like thousands of other modern SaaS websites. Good results require context — the customer's industry, audience, brand personality, competitors, undesirable references, emotional direction, typography preferences, interface density, desired interactions, product maturity, and conversion goals. AI becomes part of the exploration rather than the decision-maker.
Delivery
Eventually we presented a direction that combined elements the client had never explicitly described together. Their response was essentially: "Yes. That's exactly what I had in mind."
That is one of the best moments in a design project. Not because the designer guessed correctly — because the discovery process uncovered something the client had difficulty expressing verbally.
Outcome and evidence
Great UI/UX design is not about imposing the designer's taste on the client. And it is not about asking the client to design the product themselves. The designer sits between three worlds: the client's imagination, the user's expectations, and the realities of the product.
AI now gives us extraordinary tools for exploring that space faster. But curiosity, interpretation and communication are still what get us to the right destination.
At Envion, the objective is never simply "make something beautiful." It is: make the thing the client hoped their product could become — and make sure users know exactly how to use it.
From the engagement lead
What I’d tell anyone considering this
“The reference trap is real: clients show you three websites they love, and the obvious move is to blend them into something they technically approve of but don't recognize as theirs. The thing the client loves is almost never the thing they initially point to — you find it by giving them things to react to, not by asking them to speak design terminology.
AI changed the speed of that conversation completely. We explore a direction in an afternoon that used to take days, the client reacts, we learn, and we refine. The goal is never "make something beautiful" — it's to make the thing the client hoped their product could become.”
Evidence gate. This page publishes only what Envion's project records and client disclosure permissions support. Outcomes are added once verified against a baseline, a measurement period, and an approved source.
FAQ
Questions about this case
Facing a similar challenge?
You know what your product should feel like but can’t explain it? That’s exactly where Envion’s design discovery starts — references, reactions, and AI-accelerated exploration until you say "that’s it."
Discuss a Similar ChallengeKeep exploring
Similar case studies
Executive Technology Leadership
Support for high-stakes product and AI decisions
Bring senior technology leadership into the business when the roadmap is unclear, delivery is at risk, an AI initiative needs stronger ownership, or the company needs an experienced technical voice before hiring a permanent CTO.
Discuss Interim CTO SupportCore responsibilities
- Align product and technology priorities with business goals and measurable outcomes.
- Review architecture, delivery risks, data foundations, security needs, and AI readiness.
- Lead internal teams and external partners through a practical execution plan.
- Clarify team structure, ownership, decision rights, and delivery cadence.
- Support investor, board, partner, and due-diligence conversations with credible technical judgment.
New experience
Prompt-to-Page — try it right here
Describe the landing page you want, in your own words. We turn it into a finished page and email you a private link in 5–10 minutes — no briefs, no calls, $0 to see the result.
- Describe what you want to create.
- We structure, write, and compose the page.
- You receive a private link when it is ready.
Start with a sentence — the interactive builder takes it from there.
Generate My PageSafe, respectful content only. No obligation.