Exploration 01
Open text or guided paths
- Constraint
- Vague prompts like “tell me about design” hit dead ends.
- Trade off
- Strict menus feel like an automated phone line.
- Solution
- Quick reply chips for common topics, with open text always available.
Universidad Europea · UniCorn AI guidance
Humanising higher education discovery through conversational intelligence.
Overview
UniCorn is an AI guide for Universidad Europea. It replaces heavy course catalogues with a friendly mobile chat that takes students from their first question to a confident application.
Prototype
Problem
University website
Deep menus and jargon
Pages and PDFs written for the institution, not the student.
Blank canvas stress
An empty text box leaves people unsure what to ask.
Drop off and abandonment
Effort peaks when intent is highest.
Clear paths that still feel like a conversation.
Degree cards, maps and deadlines instead of walls of text.
WCAG contrast, touch targets and legible type on any phone.
Strategy
I mapped what students need at each stage, so the chat could move from exploring to deciding without the student noticing the switch.
UniCorn assistant
Explore and profile
Match and compare
Apply and get support
Explorations
Exploration 01
Exploration 02
Exploration 03
System
The same components had to survive low fidelity exploration, an interactive prototype and engineering handoff without being redrawn at each stage.
Foundational tokens
Conversational components
Rich module cards
Deliverables
Deliverable 01
Opens with low friction interest cards rather than an empty prompt, tuning what the assistant knows to the student's degree level and subject before the first real question is asked.
Deliverable 02
A full set of mobile viewports covering typing indicators, message grouping, inline cards and progressive disclosure, built to keep the thread free of clutter as it grows.
Deliverable 03
A brand built around the UniCorn mark, with a colour architecture chosen for legibility across whatever screen and lighting a student happens to be using.
Deliverable 04
Architectural maps documenting intent triggers, fallback states, quick reply paths and responsive component behaviour, so engineering had the whole picture rather than a set of screens.
Reflection
A good assistant is not built on prompts alone. Structuring the underlying content into scannable cards and guided paths is what turns a chatbot into something that actually guides.
Small details, a realistic typing delay, a visible processing state, an explicit confirmation step, set honest expectations about what the assistant can and cannot do.
Contrast that holds, generous touch targets and a clear hierarchy for screen readers meant the platform served every prospective student, whatever their ability or device.