Concept·Prototyping·Augmentation·Developing·CON-021

Prompt-to-Prototype

Value hypothesis

Produces functional, interactive prototypes without manually wiring hotspots or engineering support, achieving higher fidelity faster.

Innovation · Velocity

The designer describes interaction behaviors, user flows, or screen states in natural language, and the AI tool or coding assistant generates a functional code prototype.

Risks in application

Black Box Rationale

Prompted prototypes contain decisions no one can account for or explain, making designs less internally defensible and more difficult to test.

Constraint Blindness

Creates code the designer cannot read, interrogate, or explain; engineering teams may inherit unusable code.

Homogenization

Everything looks like Tailwind.

Expertise that differentiates

Interaction Design

Specifying interaction behaviors, transition logic, edge cases, and error states with the precision needed to prompt AI effectively and evaluate whether outputs match design intent.

Business Framing

Selecting what is worth prototyping, calibrating scope against the stakeholder questions that need answering, and preventing work tests the wrong hypotheses.

Technical Feasibility

Assessing code suitability for production; recognising interaction patterns or behaviors that would be impractical to replicate at scale.

AI Fluency that assures

Transparency Diligence

Being honest about which prototypes have been properly vetted and which are just drafts.

Deployment Diligence

Understanding limits and risks of prototype-to-code pipelines; assuring exploratory work is not transferred into production.

Related

Possible Indicators

New method adoption

Usage of functional code-based prototypes without engineering support

Cycle time compression

Elapsed time from specification to testable prototype relative to engineering-supported prototype baseline

Sources

Noltenius (2025). Advancing User Experience Design through Generative AI. TU Wien.

Cattapan (n.d.). How my design workflow is changing with AI. Medium.

Wen (2025). Don't Trust the Design Process. Anthropic.

Chawla (n.d.). How Top Companies Are Using AI in Their Design Workflows. UX Collective.

Orego (2025). Deep Dive: AI Moderation & Data Collection. Great Question.

Batchu (n.d.). Reimagining prototyping with AI. UX Design (Medium).

[SR-028]

Borg et al. (2025). Vibe Coding and the New Prototyping Playbook. IEEE Software.

Tholeus and Djordjevic (2026). A design system that enables humans and machines to co-create production-ready UI - at scale. Into Design Systems AI Conference 2026.

Baldwin (2026). Prototyping for the unknown. Into Design Systems AI Conference 2026.

Perez-Cruz (2026). Product Primitives: The New Material of Design System. Into Design Systems AI Conference 2026.

Stockman (2026). I'm not an engineer but I ship code: How designers can ship production code and work like an engineer. Into Design Systems AI Conference 2026.

Six (2026). Building real design systems with agents. Into Design Systems AI Conference 2026.

Wolosin (2026). Machine-Readable Design Systems for MCP and LLMs. Into Design Systems AI Conference 2026.

Fehre (2026). From falling for markdown to solving real problems with scripts. Into Design Systems AI Conference 2026.

Fung (2026). Ship It! Vibe Coding Your First Figma Plugin. Into Design Systems AI Conference 2026.

Sandu et al. (2026). Designers Who Ship: Building a Real Plugin in 48 Hours with AI. Into Design Systems AI Conference 2026.

Frost et al. (2026). AI Without the Chaos: Context-Based Design Systems to the Rescue. Into Design Systems AI Conference 2026.

Wickes (2025). Prototyping with AI. IDEO U.

Vassallo and Blumenrose (2025). State of AI in Design 2025. Foundation Capital × Designer Fund.

Author unknown (2026). State of the Designer 2026. Figma.

Irawati et al. (2025). Advancing Generative AI Collaboration in Design-to-Code Workflows: Insights from Two Empirical Studies. ACM MUM '25.