Turn User Research into portable user context for ux.md and prompts for Vibe Coding
A UX Prompt translates context-of-use information into structured guidance for AI-assisted product design. It provides relevant user needs, requirements, pain points, goals, and other human-centred context for a selected task and its individual subtasks. This gives AI design tools the detailed problem-space information needed to generate design options for each step of the user task. UX Prompts can complement broader project-level UX guidance captured in ux.md with detailed context for the specific task being designed.
Specify the activity you want to analyze. The activity can be a single task, a responsibility, or a multi-phase journey
Example: Order Pizza from a delivery service for a business meeting
Describe the activity in a single sentence without prescribing a particular product or solution.
Optionally include context such as who is performing the activity and under what circumstances.
Adding context helps make the analysis more domain-specific.
The analysis takes several minutes depending on the scope and number of tasks identified
Select a task from the task hierarchy to explore its detailed context-of-use information
Example: Order Pizza
UX Prompts can use information associated with the selected task and its subtasks
Select the UX Prompt view to see context and instructions prepared for AI-assisted product design
The prompt translates structured context-of-use information into a format that generative design tools can consume
Detailed prompts can provide context for designing individual steps within the task flow
Copy the generated context into ux.md or use task-specific prompts directly with your Vibe Coding tool
Add the general task-domain context into ux.md to provide persistent human-centred context
Use task-specific prompts to guide the design of individual steps within the task flow
Consider to copy/paste other outputs such as a object model or stakeholder information
Use the general task-domain content to provide persistent human-centred context for AI-assisted design and development.
Use task- and subtask-specific content to guide AI design tools with explicit user needs, requirements, pain points, and intended outcomes.
Use the same task-specific needs and requirements to check whether an AI-generated design actually supports what users need to accomplish.
Keep the underlying user needs, pain points, and intended outcomes stable while asking the AI to explore different ways of supporting them.
Reuse the same UX Prompt across design iterations so AI tools can explore different solutions while keeping the underlying user needs, requirements, pain points, and intended outcomes stable.
Give the AI design tool the relevant context without reading through the underlying analysis and manually assembling the information it needs.