AI Search
Senior Product Designer
2025
Background
Background
As we've all become aware, the rise of AI has fundamentally reshaped our expectations of digital experiences. Across the ecosystem, products have evolved from passive systems to intelligent, assistive tools, raising the bar for experiences that are faster, more intuitive, and better equipped to anticipate user needs.
Within this context, Affinity recognized the need to move beyond manual workflows to a more intelligent system aligned with evolving expectations. As a platform built to surface relationship insights, this meant enabling users to uncover insights and act on them more easily.
At the time, customer expectations were evolving and many began to feel Affinity was no longer meeting the baseline, pushing them toward more AI-forward alternatives. Within just a year, our survey showed a significant rise in customers planning to use AI in their daily workflows, highlighting how rapidly expectations had shifted.
While it was clear we needed to act, we wanted to do so thoughtfully, avoiding the temptation to build AI features without a clear understanding of their value.
👥 Team
I worked in a cross-functional squad that included 1 PM, 1 front-end engineer, 2 ML engineers, and a team of back-end engineers.
💼 Role
I was the sole designer and led the end-to-end design process from research and vision to final handoff.
Goals
Goals
We set out to understand how AI could meaningfully improve the product, focusing on uncovering gaps in the current experience and identifying high-value use cases. While we knew customers were increasingly asking for AI and expected it to be part of the product, we lacked clarity on what that actually meant in practice. This required a research-driven approach to understand how and where it could deliver real value.
Our goal with this work was to define a clear direction for AI at Affinity, determine how it should fit into the product experience, and identify a starting point that could deliver meaningful value quickly.
Research
Research
To kick off the research, I partnered with my PM to conduct user interviews to better understand how customers were thinking about AI. To avoid bias, we kept conversations intentionally broad, focusing on uncovering gaps in the overall experience rather than placing emphasis on AI.
After synthesizing insights, I developed a set of exploratory concepts and brought them back to users to evaluate and rank based on relevance to their day-to-day workflows. These concepts ranged from surfacing relevant connections for outreach to automating data extraction from emails and pitch decks.
Across multiple feedback sessions, the clearest need emerged: users wanted a more intuitive way to ask questions and quickly get answers from their data in Affinity. This concept ranked #1 out of 6 with an average score of 4.3 out of 5 in perceived value.
While users could technically access this information at the time, doing so required a lot of manual effort, highlighting an opportunity for us to make information access easier and more aligned with evolving expectations.
Problem
Problem
The core problem was that when users had questions about companies or people in Affinity, they relied heavily on keyword searches, filters, and manually digging through notes to find answers. In a fast-moving environment where investors are managing multiple companies and deals, speed is critical—making fast, frictionless access to information essential.
While users relied on global search to navigate companies, deals, and past interactions, it often fell short due to its rigidity and lack of flexibility. Despite some recent improvements, users increasingly expected a smarter search experience that aligned more with the capabilities of modern AI.
Assumptions
Hypothesis and assumptions
We considered multiple approaches to introducing a more natural language search and evaluated them against customer insights.
We explored multiple approaches to integrating AI, including a full-width immersive chat, an assistive modal, and an embedded experience within the global search system. While each had clear value, we needed to identify a starting point that balanced feasibility with the highest immediate impact.
Based on customer demand, high usage, and what was feasible to deliver quickly, we identified global search as the most effective entry point for introducing AI into the Affinity experience. This allowed us to introduce AI in a way that felt familiar and built on existing patterns, while laying the groundwork for more advanced capabilities.
As one of the most frequently used areas of the product, it was where users already spent the majority of their time, making it a natural place to meet them where they already are.
I partnered with my PM to define key hypotheses, assumptions, and opportunity areas for evolving our global search through AI. Our core hypothesis was that introducing semantic search into the product would enable users to find relevant information more quickly and with less effort, improving their overall efficiency.
Explorations
Explorations
After early explorations, we brought the concept back to customers and uncovered insights that challenged our assumptions:
There was still skepticism toward AI-generated results: there was a need for clearer visibility into underlying sources and greater control over how results were acted upon, rather than relying on full automation.
Keyword search still held value: its speed and responsiveness were preferred when users knew exactly what they were looking for.
There was a clear need for a more conversational experience: when queries were less defined, users preferred to refine and explore results through natural back-and-forth interactions.
The insight around the need for a more iterative experience shaped how we thought about the broader ecosystem and the future evolution of natural language search. While this was out of scope for the current work, we wanted to still account for it to ensure we were setting a strong foundation for future phases.
We identified an embedded experience within global search for moments when a new query is initiated, and an assistive experience for when the intent is to stay within and refine the current context. This distinction aligned closely with the core problem of finding information when details are fuzzy and also reduced adoption risk, as an assistive surface would sit outside the primary workflow where users spend most of their time.
Iterations
Iterations
While the insights were clear, translating them into the right experience surfaced some key dilemmas. We conducted a final round of prototype testing with customers to evaluate the options we were exploring.
Final Designs
Final Designs
Our goal was to preserve the default keyword search experience while making it easy for users to access AI-powered search, especially in cases where traditional search didn't return the results they needed.
I led the effort to define how AI should visually appear in the product. While we explored more experimental directions, we ultimately prioritized a design language that was immediately recognizable as AI to avoid confusion.
This visual system was later adopted by marketing, creating a more cohesive and consistent representation of AI across both the product and brand.
I defined a vision for a conversational chat experience that allowed users to explore results more deeply and iteratively refine their queries through dialogue. Despite being widely adopted across many products out there, users were still drawn to this pattern because it felt familiar to them and aligned with how they already interacted with similar tools.
Impact
Impact
The research, direction, and implementation plan were all presented to the executive team and helped shape Affinity's vision for AI. It also influenced many product roadmaps across teams due to its cross-functional impact.
While I wasn't on the team long enough to see this work through full implementation, early testing showed strong positive feedback from customers, which gave us confidence we were addressing their real needs and not just adding AI for its own sake.
Takeaways
Takeaways
This work came with strong leadership interest and a pressure to move quickly due to the rapid pace of AI advancements. Establishing and articulating a clear vision upfront was important to building stakeholder confidence, allowing us to move faster.
While we made progress, it was also important to keep everyone aligned since this work was dependent on many teams' roadmaps. Clear and consistent communication was critical. My PM and I regularly shared user research findings and work in progress through weekly product updates and quick Slack posts to ensure teams stayed informed.
When things move quickly, it can be easy to overlook broad communication across the organization—this work helped reinforce the importance of maintaining alignment across teams and adapting communication to different audiences.