GenAI Prompt for
UX Writing
Industry
ECommerce
Company
Lycle
Year
2025
about.
As Lycle scaled, product language drifted across screens. In high-trust flows like checkout, cancellations, and error states, this inconsistency reduced clarity and trust. I owned the UX Writing Guidelines initiative and packaged it into a generative AI prompt framework so the team could produce consistent, guideline-compliant copy faster with less review overhead.
Building Lycle's UX Writing foundation from the ground up
why.
While working on funnel improvements, I noticed the same language issues repeating across screens. The intent stayed the same, but wording changed depending on who last touched the UI. I shared a few examples and asked whether we were comfortable letting the product voice drift as we scale.
This started with a conversation in our Design chapter Slack
challenge.
The biggest obstacle was visibility. Copy was scattered across components, hard-coded flows, dynamic states, and failure-only edge cases, so we couldn’t standardize what we couldn’t see. The second challenge was adoption, because a guideline doc alone doesn’t change behavior unless the workflow makes it easy to follow by default.
Audit insight: Product-wide tone inconsistency identified.
how.
I ran the work in three steps: audit, align, and operationalize. First, I created a complete view of product strings and tagged recurring issues like tone drift, missing next steps, and terminology inconsistency. Then I facilitated cross-functional alignment on voice, terminology, and where templates should be strict so decisions wouldn’t reset every sprint.
Audit kickoff:
Partnered with engineering to extract copy data across the platform
Audit dataset:
Organized the strings in a spreadsheet and shared it with the team
Team workshop:
Aligned on issues and direction based on the audit findings
Feasibility check:
Dev team to validate implementation of the workshop decisions
execution.
I built the guideline as a compact, operational system teams could apply quickly. It started with a voice framework (mission, promise, story), then expanded into writing principles, scenario patterns, and strict templates for high-risk cases like errors and policy messaging.
Voice framework: Defined the brand voice through mission, promise, and story.
Core values: Translated product values into actionable writing properties.
Principle brainstorming: Explored tone, clarity, and reassurance for beginner guidance.
Persona definition: Defined the product voice as a warm guide for beginners.
principle.
I translated the voice framework into three writing principles that could guide everyday product decisions. These principles helped teams write with more consistency and clarity by defining how to respect users, simplify language, and maintain trust across the platform.
Writing principles: Established clear UX writing rules with do and don’t examples.
final look.
I turned the guideline into a scalable workflow by combining documentation, reusable prompt structure, and tool integration. This allowed teams to reference standards, generate guideline-compliant copy faster, and apply the system directly within their product workflow.
Operational guideline: Compiled the UX writing rules into a structured, team-ready guideline.
Unified AI prompt: Converted the guideline into a reusable AI prompt for consistent copy generation.
