AI workflows for designers. UI prototyping, design systems, visual exploration, and creative tools.
Build a 3D dungeon crawler and a framework for community contributions. This advanced workflow uses a custom 'skill' in ChatGPT Sites to allow others to build and add new game levels using natural language.
Go beyond generic icon libraries by prompting an AI model to create custom, characterful SVG icons. This workflow shows how to get unique, well-designed icons for your projects by providing simple, clear descriptions.
Leverage Claude Opus 5.5 to instantly generate unique, stylistically consistent SVG illustrations or icons from a simple text prompt. This is perfect for designers and marketers needing custom visual assets without design software.
Delegate tedious production design work to an AI assistant. This workflow shows how to use a custom bot connected to Figma to handle repetitive tasks like icon placement, freeing you up for more creative work, all from your phone.
Use a hybrid AI workflow to bridge design and development. Generate high-level design concepts and tokens with Claude, then use Codex for robust implementation of the technical components in your codebase.
Learn to translate fashion sketches into a full suite of marketing visuals. This workflow covers creating a detailed design spec, generating a core product photo with AI, and iterating for different contexts like runway and influencer shots.
Leverage Claude Opus 5's powerful but verbose nature to create detailed front-end prototypes. This workflow focuses on asynchronous generation and blunt feedback to get high-quality outputs without getting bogged down in frustrating chat interactions.
Implement a feedback loop to translate subjective expert feedback into quantitative evaluation criteria. This workflow allows you to scale the 'taste' of key stakeholders, like a lead designer, across your entire AI system, continuously raising the quality bar.
Create a repeatable exercise demonstration by pairing a consistent AI character with a real motion reference.
Extract the real colors, type, spacing, and components from your repositories into a portable HTML design system. Reuse the file as visual context for new interfaces and component variations.
Build and iterate on high-fidelity prototypes directly in your browser. This workflow uses a custom web UI to generate designs from prompts, visually annotate feedback, and automatically implement revisions with AI.
Generate a multi-page brand-kit concept with GPT Images 2.0, then use real visual references to push the result toward your brand.
Use a live website as context for a functional redesign prototype while preserving the product’s real content and flows.
Export the states that exist in code but are missing from the design file. One prompt asks the agent to find every state in a flow, place editable versions side by side in Figma, and give designers a current canvas for refinement.
Build a repeatable Midjourney brand system by testing a visual mood board, isolating the style references that actually work, layering in a personalization code, and documenting the final recipe for reuse.
Turn a spoken product idea into a working prototype by pairing plan mode with repository context, a live preview, and browser checks the agent can run without handing every validation step back to you.
Use Midjourney to explore a mascot or character before production illustration, treating variation as evidence for the design decisions the team must make and turning the selected traits into an original, rights aware style guide.
Turn a static Figma direction into a disposable interactive prototype that reveals responsive, resizing, toggling, and edge behavior, then hand engineering the decisions and evidence rather than presenting prototype code as production code.
Refine a generic generated interface by diagnosing hierarchy and interaction problems, translating strong references into explicit design principles, and iterating one controlled layer at a time while preserving content, accessibility, and real behavior.
Create a reusable Cursor playground for interactive prototypes, then build a small digital piano whose visual keys, keyboard input, audio engine, focus behavior, and mobile interaction are explicit and testable.
Use Cursor as a visual brainstorming partner by asking for concrete aesthetic vocabularies, combining selected properties with permitted references, and exploring several reversible branches before choosing a direction.
Capture a useful interface pattern from a live product with the Magic Patterns extension, convert it into a reusable component, and improve the primitive once so every later prototype benefits.
Turn screenshots of your product into a reusable v0 component library, then fork that library to prototype new pages without losing the visual language your team already recognizes.
Turn a loosely stated stakeholder idea into a clickable prototype during the conversation, then use the prototype to surface missing logic and align leaders, engineers, and customers before the team commits to a build.
Use index cards to explore a mobile flow anywhere, then give the photographed sequence enough product and platform context for an image model to refine it before rebuilding the result with real Figma components.
Build a more credible product prototype by defining representative structured data before generating the interface, then swap and stretch that data to expose layout and product assumptions that polished placeholder content would hide.
Explore an AI feature in Magic Patterns by adding it to a recognizable base UI, generating genuinely different interaction models, and comparing the working prototypes against user and product criteria with design and engineering partners.
Design a conversational AI feature from the experience backward: write golden conversations, test them across representative scenarios, define the quality rubric they reveal, and turn the strongest flow into a clearly labeled interactive prototype.
Turn a PRD into a clearly labeled local prototype, test the critical path with mock data, repair visual defects from screenshots, and improve the design with concrete references and accessibility constraints.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.