Enhancing Efficiency with AI-Powered Conversational Search and Summarization
Role: Product & Design Lead (Discovery & Strategy)
Scope: AI-powered conversational search and summarization for Hayes (healthcare and clinical insights)
Timeline: 3 months
Impact: Reduced manual effort, improved information retrieval speed, and established an AI foundation across products
Overview
Healthcare professionals at Hayes spend significant time searching, validating, and summarizing clinical study findings, policy and appeals data. I led the exploration and definition of an AI-powered solution to streamline this process—balancing speed to market with long-term scalability.
The Situation
Hayes users—policy writers, clinicians, and appeal specialists—operate in a high-stakes environment where accuracy and speed are critical.
Their workflows required:
Searching across multiple documents
Manually extracting relevant information
Synthesizing findings into summaries
This created friction at every step:
Slow turnaround times
High cognitive load
Increased risk of errors
The existing search experience wasn’t built for how users actually worked.
The Problem
The core issue wasn’t just “search”—it was decision-making inefficiency.
1. Fragmented Information Retrieval
Users had to manually scan multiple documents to find relevant answers.
2. High Effort Summarization
Even after finding information, users still had to interpret and condense it themselves.
3. Accuracy & Trust Risks
Manual workflows increased the likelihood of missed or misinterpreted details.
4. Lack of Workflow Integration
Search results didn’t align with how users actually completed tasks like:
Policy updates
Appeals review
Coverage verification
Why This Was Hard
High-stakes domain (healthcare decisions require precision)
Low trust in AI outputs without transparency
Cross-functional complexity (design, engineering, research, GTM)
Ambiguous starting point (no clear “right” AI pattern yet)
We weren’t just designing a feature—we were defining how AI should behave within the product.
Strategy
We aligned around a clear hypothesis:
If we provide AI-generated answers with clear sourcing, users can complete complex workflows faster, with less effort and greater confidence.
This led to three priorities:
Start narrow with high-value use cases
Prioritize trust and transparency
Ship quickly to validate adoption
Discovery Workshop Board
Vision Statement
Design jam
Effort/Value Matrix on our design jam ideas
Key Decisions
1. Start with a Focused MVP (Not a Full AI Assistant)
We scoped Phase 1 to summarization and conversational search within a contained experience.
Why: We needed to validate usefulness before expanding scope
Tradeoff: Limited functionality, but faster learning
2. Separate AI from Core Search (Initially)
We introduced AI in a dedicated surface instead of embedding it directly into existing workflows.
Why: Reduced risk and allowed controlled testing
Tradeoff: Added friction vs. fully integrated experience
3. Design for Iteration, Not Perfection
We structured the roadmap into progressive milestones:
Phase 1 (“Roller skates”) → Core summarization + feedback
Phase 2 (“Electric scooter”) → Ratings, saved results, history
Phase 3 (“Sports car”) → Prompt guidance + deeper interaction
Why: AI quality and trust improve through iteration
Tradeoff: Early versions feel incomplete but enable faster validation
4. Prioritize Trust Signals Early
We emphasized:
Source visibility
Feedback mechanisms
Why: Adoption depends on user confidence in AI outputs
How I Led the Work
I led the initiative from discovery through execution strategy:
Discovery & Alignment
Facilitated cross-functional workshops (design, product, engineering, research, GTM)
Synthesized user pain points into clear opportunity areas
Defined the initial product vision
Vision + Strategy
Translated ideas into a phased execution plan
Scoped MVP to balance speed and value
Defined milestones aligned to learning goals
Execution Support
Partnered with designer to shape the user experience
Ensured alignment across teams as we moved toward delivery
Solution
Phase 1 delivered:
AI-powered summarization
Conversational search interface
Feedback capture for continuous improvement
The experience allowed users to:
Ask questions directly
Receive synthesized answers
Reference supporting sources
Rollerskates
Electric Scooter
Sports Car
Watch it work!
Click the video above to watch me interact with our shipped AI Phase 1 solution.
Early Results & Learnings
What worked:
Users saw immediate value in reduced manual effort
Summarization accelerated information processing
Where we saw friction:
Users were hesitant to fully trust AI outputs
Citations lacked precision (needed section-level linking)
Users expected AI answers at the top of results (Google-like behavior)
These insights directly informed Phase 2 priorities.
What This Enabled
Established an AI interaction pattern across the product
Created a foundation for scalable AI capabilities
Enabled faster iteration based on real user feedback
What This Demonstrates
Leading 0→1 product exploration in ambiguous spaces
Translating AI potential into practical, testable solutions
Balancing speed, scope, and user trust
Driving alignment across cross-functional teams
Designing for learning and iteration, not just delivery
Final Takeaway
This work wasn’t just about adding AI—it was about redefining how users access and act on information.
By starting small, prioritizing trust, and iterating quickly, we turned a complex, manual workflow into a foundation for faster, more intelligent decision-making.