A Career Copilot for navigating opportunities and mapping skill gaps

I led the product vision and design strategy for Career Inspiration, an AI-powered Copilot that reimagines how students navigate their potential careers. By creating an intelligent skills-matching framework, we built an experience that empowers students to discover career paths while providing transparent, data-driven insight into their unique strengths and skill gaps.

My primary objective was to transform a proprietary dataset of over 130,000 graduate jobs into a discovery product capable of serving thousands of students during the high-stakes university enrolment window.

As UX/UI Lead, I defined the strategy for the AI interaction patterns that made the tool both commercially viable for our university partners and a genuinely good experience for students. The product operates on a B2B2C model, architected to be white-labelled so institutions can capture and engage 100% of the first-year cohort at the point of entry.

To achieve that scale, I guided the team through the development of a chat-first interface and a guided routing framework that seamlessly maps student skills to career pathways.

Students perceived our playful, social-media-style swiping interface as a novelty, which undermined the platform’s credibility for high-stakes career decisions. Our Gen Z audience embraces expressive, highly stylised UI in casual daily apps like TikTok or Deliveroo, but they draw a clear line when it comes to their professional futures. For career-shaping milestones they demand a clean, simplified experience that prioritises high-utility, actionable information.

Based on these insights I pivoted the design strategy, moving away from gamified swiping mechanics in favour of structured cognitive funnels that respected the seriousness of our users’ professional ambitions.

To solve the black-box problem of AI, I established a foundational interaction pattern for the product: the Command Centre. The architecture relies on a dual-pane interface designed for visual feedback: a central chat extracts user intent while a fixed sidebar visualises their interactions in real time.

By keeping a human in the loop we created a highly predictable mental model. Students can instantly verify, tweak and edit the LLM’s “learnings” live, turning what is usually a mysterious, probabilistic process into a transparent, high-trust interaction that is actually useful.

By pre-populating existing student data, such as course enrolment and pre-stated sector interests, into the onboarding state before the LLM’s first prompt was even generated, we dramatically shortened the path to value. This architectural choice kept the conversational UI focused purely on extracting high-level intent, while the system quietly calculated matching career options in the background.

Initially we matched students directly to scraped job listings, but user testing revealed this was overwhelming and cluttered with duplicate roles. So we pivoted the data model from raw listings to a curated taxonomy of career pathways. Matching students to high-level pathways first focused the experience on long-term career discovery, with clean data on salary ranges, typical roles and historical placements, and only surfaced live, active roles once a student chose to explore deeper.

Designing encouraging match states. We also had to design the psychology of the matching classifications. To keep students inspired we rejected discouraging labels like “weak match” and clinical percentages, opting instead for a supportive hierarchy of Super Match, Match and Partial Match. Rather than signalling a dead end, a Partial Match serves as an encouraging transition: in the final profile summary we pair it with specific skills to develop, transforming a student’s skill gaps into a clear, actionable roadmap for future growth.

Students often arrive at advising appointments with no direction and little self-awareness of their capabilities, so the tool acts as a comprehensive pre-appointment diagnostic. By mapping a student’s existing skills against real-world industry requirements, the interface immediately identifies their Super Matches and visualises their specific skill gaps, giving both the student and the advisor an instant, data-driven starting point.

This shifted the advisor’s role from basic discovery to high-value coaching: students arrive with a validated vocabulary of their own skills, and the summary report was designed to be advisor-ready from day one.

An aggregated data reporting engine for universities. By capturing real-time student interactions, tracking precisely what they ask the AI and how they self-assess their capabilities, we unlocked a level of macro insight institutions previously had no way of accessing.

For the first time, universities can identify systemic skill gaps across their entire student body, pinpointing competencies a whole cohort might be lacking. It turns what used to be a feedback black hole into a strategic goldmine: exactly the data needed to tailor workshops, adjust curriculum focus and proactively address the shifting needs of their students.