Minerva
Role
Sole UI/UX Designer
Scope
Mobile, Desktop Web App, Conversational AI UX
Duration
July 2025 – October 2025
Overview
I joined a fast-paced 2-person engineering team to elevate an existing mobile prototype into a production-ready, cross-platform product. Over a sprint, I led the end-to-end design for an AI Tutor conversational chatbot, built a unified light/dark design system across mobile and desktop, and designed monetisation and setting flows.
Key Design Decisions & Strategy
DESIGN 1
Conversational UX & Prompt Engineering for AI Tutor
Designing guided response loops and multi-window document views for complex study workflows.
1.
Action-Based Suggested Prompts
Benchmark-researched conversational UI to design context-aware action chips that guide students after every AI response, eliminating dead-ends.
2.
Defining Distinct Study Modes
Co-designed prompt-mode logic with engineering to ensure students could easily differentiate between various AI response style.
DESIGN 2
Responsive Multi-Window Layouts
I introduced tabbed views for mobile and scalable side-by-side expandable panels for desktop web when viewing source documents alongside chats was required.
DESIGN 3
Cross-Platform Design System & System Audit
Converting mobile screens to desktop web required more than basic scaling—it required a unified visual language. Adaptable UI patterns accommodated shifting backend capabilities without breaking the user experience.
DESIGN 4
Monetization UX & Copy Strategy
Structured pricing tiers to give users full transparency while strategically highlighting premium AI features to drive plan upgrades and business revenue.
Managing Mid-Sprint Scope & Future Roadmap
1.
Evolving Platform Capabilities
Designed state-flexible layouts capable of handling platform-specific constraints, such as differing image-occlusion workflows between web (manual) and mobile (automated).
2.
Future-Proofing for Gamification
Designed early structural frameworks for a 6-month roadmap, including subject-wise card decks, XP/streak leaderboards, performance analytics dashboards, and AI-powered self-explanation badges.
Learning Outcomes
Effective AI design requires balancing open-ended conversational freedom with guided UI guardrails.
Don't rely solely on a blank text box; use suggested prompt chips, action buttons, and clear mode selectors to guide users toward valuable outcomes.
When joining a project mid-flight, retrofitting existing screens into a structured component library pays off immediately when scaling to new platforms like desktop.