AI Search
Senior Product Designer
2025
Problem
Users relied on keyword searches, filters, and digging through notes
The core problem was that when users had questions about their data in Affinity, they relied heavily on keyword searches, filters, and digging through notes to find answers. For investors managing multiple deals, this made quick and easy access to information critical.
While users relied on global search to navigate, it often fell short due to its rigidity. Even with some recent improvements, users still expected a smarter search experience.
Approach
Where should we start?
We explored multiple approaches to integrating AI into Affinity, which included a full-width immersive chat, an assistive modal, and an embedded experience within global search. While each of these offered value, we needed to identify a starting point that balanced feasibility with the highest immediate impact.
We identified global search as the most effective entry point for introducing AI into the product. As the most frequently used features of the product, it was where users already spent a lot of their time, which made it a natural place to meet users where they already were.
Our core hypothesis was that introducing semantic search would enable users to find information faster and with less effort, improving their overall efficiency and satisfaction.
Iterations
Bridging insights to our solution
While the insights were clear, translating them into the right type of experience surfaced a few key dilemmas. We conducted a final round of feedback with customers to evaluate options we were exploring.
Final Designs
Evolving the system while preserving what works
Our main goal was to preserve the default keyword search experience while making it easy for users to access an AI-powered search, especially in cases where traditional searches didn't return the results users needed.
I led the effort to define a visual system for how AI would be represented across the product. While we explored more experimental directions, we ultimately prioritized a design language that was more recognizable and leveraged patterns users were already familiar with. This system was later adopted by marketing, which unified the product and brand experience.
Zooming out, the vision was to transform Affinity from a platform where users manually uncover insights into an intelligent partner that works alongside them. The chat experience was our starting point, but the long-term vision was a proactive system that surfaces recommendations, insights, and opportunities at the right moment.
Impact
Establishing a shared vision across the org
The strategy and implementation plan were later presented to the executive tea and helped shape Affinity's AI vision, which was later shared with customers at Campfire 2025.
While I wasn't on the team long enough to see semantic search through its full implementation, early feedback showed positive indicators from customers and a clear alignment with their expectations.