Internal platform search
Role: lead designer
Situation
Atheneum's internal platform required significant manual effort to locate relevant experts, often producing inaccurate results.
Task
Our goal was to improve the platform’s search functionality, making it more intuitive and enabling staff to efficiently find the right experts based on context, not just keywords.
Project success
🎯 Better search results by using AI to understand the context, not just matching keywords.
🎯 More efficient search interface that saves time for internal teams.
🎯 Fewer searches needed to find the right experts for projects.
Action
We conducted user interviews with internal teams to identify pain points, then built a coded prototype to test with real data. We incorporated AI to enhance search relevance by understanding context, not just keyword matching.
Result
The improved search interface provided better results, added more experts to projects in fewer searches, and increased efficiency by allowing flexible criteria and AI-driven suggestions.
Outcome
The revised search interface was released as part of a phased release structure and we continue to speak with users to iterate and improve. Overall we found the new interface improved our internal teams daily-to-day when it came to locating experts.
Personal highlights
Making daily work easier for staff
Working with data science teams to improve how users search for information, using AI to understand what they're looking for and give better results.
Learning more about search systems and the many unique situations that can come up is important and shouldn't be overlooked.
Note: this case study follows the STAR framework and is intentionally concise to provide a brief overview of the project. If you'd like to learn more, please feel free to reach out!