AI Search
Senior Product Designer
2025
Problem
Keeping pace with changing expectations
As a platform built to help investors uncover insights, Affinity recognized the need to evolve beyond manual workflows and align more with what customers expected of digital experiences as AI became more prevalent.
Expectations were shifting quickly and many customers felt Affinity was no longer meeting their baseline needs. Within just a year, our survey showed a significant increase in teams planning to incorporate AI into their workflows, which highlighted the opportunity to rethink how the product could better support them.
Growing customer demand and the evolving AI landscape created a strong sense of urgency among leadership and we knew we needed to move quickly to avoid falling behind the market.
Approach
How can AI deliver meaningful value?
Although we knew that AI needed to become part of our broader strategy, we didn't want to just add an AI chat experience because everyone else was doing it. We wanted to understand where the real need was and identify how AI could solve actual problems and deliver genuine value.
I led a round of interviews with some of our largest customers to better understand their pain points in the current experience, how they were using AI today, and where they felt Affinity was falling behind.
Since Affinity is a relationship intelligence platform, users spent a significant amount of time evaluating relationship strength, gathering context, and determining the right person to engage for a potential opportunity. A lion's share of this process was manual and prone to blind spots since information was fragmented across emails, notes, and CRM records.
We learned that some customers were even resorting to third-party AI tools, like ChatGPT and Perplexity, to manually piece together insights outside of Affinity, which was a strong signal that the product wasn't supporting their workflow. We saw an opportunity for AI to synthesize this fragmented information and help users make faster and more confident decisions.
Hypothesis
Finding information hypothesis
We hypothesized that introducing AI into the CRM could help synthesize relationship data across emails, meetings, and notes and help users to identify the right people to engage more quickly and confidently.
This could address gaps in the existing experience and increase engagement by making Affinity more valuable within customers' everyday workflows.
Iterations
Building value through incremental changes
We learned agentic workflows of an assistant helping alleviate the manual burden was key.
An insight we learned was that these were supposed to help, but not be key decision makers.
Before we could jump to a system that was proactive and make recommendations, we needed table stakes as Affinity didn't even have a way to semantic at all.
We wanted an easy way and the future was chat, but we didn't want people to ignore it in the corner and we wanted adoption so we chose a highest touch point of global search. In hindsight, I feel like we should have tested this and not assumed it if I could do it again.
So our stages were like this.
Search > Proactive recommendations > Automation
After sharing our concepts with customers, we uncovered some insights that challenged our initial assumptions:
Trust remained a barrier: Users were skeptical of AI-generated results and wanted greater transparency into why results were surfaced and what sources they were based on.
Sometimes they didn't know what they wanted.
Keyword search was still important and not a replacement
We addressed some of these insights through a series of design refinements.
Worked with ML engineers alongside them as they built the chat system. Some constraints and issues was inaccuracies. How could we account for that? When results aren't what users want. Create a workaround for an imperfect result.
Trust remained a barrier > Cite sources
Chat system larger vision
Toggle between keyword search
Initially wanted to embed the results, but since keyword search showed real-time results as users typed, AI search operated differently and required users to press "Enter". So two different interactions in the same modal.
We explored seperate toggle.
It was getting lost, so the affordance needed to be clearer.
Final Designs
Building toward an experience that reflects how people work
We presented our AI strategy to the broader organization and shared our vision of evolving Affinity into an agentic partner that proactively helps users through their workflow. We also introduced a phased roadmap outlining how we planned to bring that vision to life with semantic search positioned as the first milestone. Framing semantic search as the foundation for our broader AI strategy gave teams visibility into the long-term direction of the product and helped them understand how it would influence their own roadmaps.
Establishing AI design principles was important since AI would shape experiences across the product. We defined a consistent framework so every AI interaction could feel predictable, familiar, and in alignment with user expectations, which made the experience easier to understand and trust.
Accounting for load states and searching through sources was too difficult to implement, so I made best with the just communicating baseline.
Impact
Sharing our long-term AI strategy
The AI strategy and semantic search initiative laid the foundation for Affinity's broader AI roadmap and were introduced to customers as part of our future vision. Early feedback confirmed that semantic search solved an immediate pain point while demonstrating the long-term value of our AI direction.
Takeaways
Design's role in creating clarity and alignment
The AI initiative drew significant leadership attention and cross-functional visibility, as multiple teams relied on it to inform their own roadmaps. Keeping everyone aligned was just as important as designing the product itself. We regularly shared customer research, design explorations, and work in progress through weekly product reviews and Slack updates to ensure teams had visibility into key decisions and the rationale behind them.
Equally important was communicating the long-term vision. By creating hi-fi concepts early on in the process, we gave stakeholders a tangible view of where we were headed. This helped build alignment around the broader strategy, why semantic search was the right starting point, and how each milestone contributed to the future direction of the product.
This project helped reinforce to me that design extends beyond just the interface, especially in emerging spaces like AI. It plays a critical role in aligning teams around a common vision and helps us navigate ambiguity with confidence.