Design & AI Workflow
When to Use AI, When to Hire a Designer: A Real Experiment
By Entify design team
·
5 min read
·
5/1/2026
We gave the exact same detailed text prompt to two AI tools — Claude Chat and the newly released Claude Design — with no Figma mockups attached. Not because we didn't have them — but because most startup founders don't.
Bring in a designer when the work shifts from "does this concept work" to "does this product feel exactly right."
The workflow We'd recommend to any founder
Based on this experiment — and on working in design across early-stage products — here's a practical roadmap. Not theoretical. Not defensive about AI. Just what actually makes sense given the tools that exist today.
When do you actually need a designer?
Here's a practical guide, not a sales pitch.
The key insight in this roadmap: AI is most powerful at the two ends — rapid prototyping at the start, precise development at the end. The middle phase — where the product's specific feeling and visual identity are defined — is where human design judgment matters most. Not instead of AI. Alongside it.
The core insight
AI understands your users. It processes your pain points. It can build a working prototype that a real person can interact with in minutes. That's genuinely remarkable, and founders should be using it from day one.
What AI can't do is hold the full weight of a design intention — the accumulated reasoning behind micro-decisions that together define how a product feels to use. That's not a flaw. It's just where the human designer's work begins.
Real Experiment: Making an app with AI tools
Both tools read the brief with a level of UX intelligence that genuinely surprised us.
This matters for founders. If you write a clear brief with a well-defined target user and specific pain points, AI tools will act on that UX intent with impressive accuracy. The days of needing a designer just to get a working prototype with coherent UX logic are genuinely behind us.
Where the two tools diverged
Claude Chat and Claude Design have different strengths, and understanding the difference will save you real time and money as a founder.
The gap between intent and execution
The Figma mockup is the benchmark in this experiment — not because it's perfect, but because it represents fully-held design intent, built independently before a single AI prompt was run. Every decision in it was made deliberately, with awareness of every other decision around it. The dial has no value ring because the user can hear the change in real time — the sound is the feedback. The dropdown has no box because the visual weight of a border would break the spatial rhythm of the hex channels. These weren't happy accidents. They were choices, made in sequence, each one informed by all the others.
AI doesn't know the reasoning behind those decisions. It sees the instruction, makes a judgment call about what's conventional and safe, and executes that. Which is often right. But not always — and for a product whose quality is core to its value, "often right" isn't enough.
That gap — between "clean and functional" and "precise, warm, alive" — is where a human designer lives.
It's not a technical gap. It's an intentional one.
And that knowledge shapes every other decision in the product.
What "the feeling of the product" means in practice
Every product creates a feeling when you use it — whether the designer intended it or not. Notion feels calm and organised. Duolingo feels playful and encouraging. A banking app should feel safe and trustworthy. Lull was designed to feel like picking up a snow globe: immediately beautiful, effortless to start, with a sense of something alive happening on screen.
These feelings don't come from one big decision. They come from hundreds of small ones made consistently: the spacing between elements, which information is shown and which is hidden, how a button responds when you press it, what happens in the moment between one screen and the next. AI can execute individual decisions well. What it struggles to do is keep all of these small decisions pointing in the same direction — toward one consistent feeling — especially when that feeling is subtle rather than obvious. That is the work a human designer does.
You'll know when your product feels like a snow globe. The question is whether you have someone who knows how to build one. Learn more about our design approaches at entifydesign.com/our-works.
