Skip to content
FREN Book a call
( AI · Workflow )

Generative AI in a product design workflow: what actually works

Three years of generative AI on real products. Five uses held up, three disappointed, and one principle stood out: the machine amplifies intent, it never replaces it.

· 3 min read · AI · Workflow

Generative AI in a product design workflow: what actually works

( Key facts )

Five uses of generative AI hold up in production: research synthesis, flow and content variants, prototyping in code, design system documentation, visuals on a tight budget. Three disappoint, and one principle remains: AI amplifies intent, it never replaces it.

Author
Vladimir Spalaikovitch, Senior UX/UI Designer, Product Designer and Digital Art Director
Published
Updated
Reading
3 min · 645 words

In a product design workflow, generative AI is good for five things that have proven themselves in production: synthesizing user research, generating flow and content variants, prototyping in realistic code, documenting and checking a design system, and producing visuals on a tight budget. It replaces neither understanding the problem, nor making trade-offs, nor owning the outcome.

What I tested, and on what

Since 2023, I have used generative models on my own products (WeeFizz, Reformer Society) and on client work (Climeet, websites and landing pages). This field report separates what lasted from what ended up abandoned.

The five uses that hold up

1. User research synthesis

Interview transcripts, support tickets, customer reviews: the model groups, counts and quotes. A round of ten interviews gets synthesized in a day instead of a week. The condition: a prompt that forbids inventing quotes and asks the model to flag what the data does not support. And a full review, because the model smooths over contradictions.

2. Flow and content variants

Three alternative structures for an onboarding, five wordings for an error message, two ways to split a form. AI excels at producing alternatives quickly. The designer chooses, and justifies the choice. The gain is not the speed of producing the final choice, it is the breadth of exploration for the same budget.

3. Prototyping in code

This is the use that changed my work the most. A coding agent produces a realistic front-end prototype in a few hours: data, states, responsive layouts, interactions. I finish it by hand. The prototype gets tested with real users and handed to developers as a reference. The line between mockup and product has moved. See front-end development.

4. Design system: documentation and checks

Writing the documentation for forty components from the actual components, spotting naming inconsistencies between Figma and code, generating a component's missing states while respecting the tokens: repetitive tasks the model does well, under supervision. Two days instead of two weeks for the initial documentation.

5. Visual production on a budget

Campaign visuals, illustrations, format variations, demo visuals when there is no photo budget. On WeeFizz, twelve demo sites got their visuals through generation, with a locked prompt system that guarantees consistency. The condition: precise art direction upstream, and strict selection downstream.

The three uses that disappointed

  1. Generating final screens as images: pretty, inconsistent, impossible to build. Useful for a moodboard, not for a product.
  2. Replacing user testing with synthetic personas: the model confirms what you told it. It does not know your users.
  3. Automating prioritization decisions: the model produces a plausible matrix, but it knows nothing about internal politics, technical debt or the client threatening to leave.

The guardrails

  • Precise context: design system, tokens, references, no-gos. Without context, the model produces the average of the web.
  • Explicit quality criteria in every prompt, and a self-check requested from the model.
  • Systematic human review of everything that comes out, especially what looks right.
  • A usage policy: what you hand to AI and what you don't (personal data, decisions, commitments).
  • Versioned prompts, treated like components: see Prompt engineering for designers.

What it changes for the profession

Production time goes down; decision time does not. The designer who thrives is the one who can frame, choose and stand behind the result. The one who only produced is now competing with a prompt. The rising skill is not knowing how to use AI: it is knowing what you want precisely enough to tell it. That is why I describe prompt engineering as a design practice, and why I offer it as an area of expertise.

One last principle

The machine amplifies intent. It never replaces it.

If the intent is clear, AI multiplies it. If it is vague, AI produces vagueness with confidence. The designer's work starts and ends there: knowing what you want, and why.

( FAQ · 03 )

Frequently asked questions

Which AI tools should a product designer use in 2026?

A large language model for synthesis, writing and reasoning (Claude, GPT, Gemini), a coding agent for prototyping (Claude Code, Cursor or similar), an image generation tool for visual exploration, and Figma with its AI features for production. The rest depends on the context.

Can AI generate interfaces that are usable as is?

It generates fast first drafts that are often structurally sound, especially in code. Hierarchy, consistency with the design system, states and polish remain the designer's job. Count on AI for 60% of the way and on the designer for the 40% that makes the quality.

How do you stop AI from producing generic interfaces?

By giving it precise context (design system, tokens, references, no-gos) and explicit quality criteria, then reviewing everything. Without context, a model produces the average of the web: interfaces that are correct and forgettable.

( Next · 03 )

Keep reading

  1. Prompt engineering for designers: the seven-block method

    A prompt engineering method for UX/UI designers: a seven-block prompt (role, context, objective, constraints, style, output, quality) and three full examples.A seven-block prompt for UX/UI designers, with three examples. · 4 minRead
  2. Prompt engineering and prompt design for design teams

    Prompt engineering and prompt design for product teams: reusable prompt systems and AI workflows for user research, UI and design systems. Let's talk.Prompt engineering for design teams: reusable prompts and AI workflows.AI · Prompt EngineeringRead
  3. Front-end development: a designer who codes

    UX/UI designer who codes: realistic prototypes, pixel-perfect HTML, CSS and React front-end development, fast static websites and hands-on developer support.UX/UI designer who codes: realistic prototypes and HTML, CSS and React builds.Design · DevRead