Content
Designing Trust in AI Recommendations
Using AI to accelerate research, prototyping, and ideation during a 3-hour winning design challenge.
Design Team
Sarah Garrison, UX Researcher
John Murphy, Principal UX Designer
As part of an internal AI Design Challenge, our team was tasked with designing an experience that helps banking teammates understand, trust, and act on AI-generated financial recommendations.
The design prompt centered around a fictional teammate, Nora, who had received several AI-generated recommendations for a client based on banking data. The AI-generated had Nora recommend her banking client to:
Open a savings account
Apply for a cashback credit card
Speak with an investment advisor
The real challenge was creating confidence around these recommendations.
If a teammate couldn't answer:
Why was this recommendation generated?
What evidence supports it?
Can I trust this?
What should I say to the client?
then the recommendation had little value regardless of its accuracy.
How might we help teammates trust AI-generated recommendations enough to confidently discuss them with clients?
One of the biggest constraints was time.
The challenge required every team to conduct user research while also producing final UI designs and a working concept. With only a few hours available, my team intentionally ran research, design exploration, and prototyping in parallel rather than sequentially.
In a traditional workflow, we would:
Research → Insights → Design → Prototype
Waiting for research would leave very little time to design so we created a simultaneous workflow:
Research → AI Exploration → Initial Concepts → Insights →
Refine & Validate → Final Prototype
AI became the bridge between these activities.
One of my goals during this challenge was to use AI as an accelerator without outsourcing design judgment.
Copilot as a Strategic Thinking Partner
Immediately after receiving the challenge brief, I used Copilot to accelerate exploration.
Instead of spending large portions of our allotted time brainstorming from a blank page, I leveraged Copilot to:
Explore AI transparency patterns
Investigate trust-building approaches
Generate alternative interaction models
Evaluate different methods of surfacing supporting evidence
Copilot reduced the time required for concept generation and allowed the team to spend more time discussing tradeoffs and making informed design decisions.
Figma Make for Rapid Prototyping
As concepts emerged, I used Figma Make to help me rapidly visualize concepts and interaction patterns.
However, I rarely used generated outputs as-is. I treated Figma Make as a sketching and exploration tool:
Generated multiple concepts
Pulled elements I liked from different versions
Combined and remixed patterns
Removed complexity that didn't support the experience
As the design evolved, manually designing in Figma became more effective than continuing to iterate through prompts. The final solution was assembled by hand, informed by insights gathered through multiple AI-generated explorations.
This dramatically shortened the gap between idea and evaluation. The final output emerged from combining AI-generated ideas with design judgment and research findings.
Key Findings
01 Comfort Discussing Financial Products
73.8% of participants reported being familiar with discussing financial products or recommendations with clients.
02 Comfort Discussing AI Recommendations
76.3% reported feeling somewhat or very confident discussing an AI-generated recommendation with a client.
Biggest Concerns
Participants identified several trust barriers:
The recommendation may not fit the client's needs
There is insufficient context behind the recommendation
The recommendation could be incorrect
Most Important Information that Builds Trust
When evaluating recommendations, participants reported that confindence increased when they are able to see:
The recommendation itself
Why the recommendation was generated
The client benefit
Supporting customer data
(Research findings taken from our UserTesting survey summary.)
Design Principles
01 Explain recommendations
Explain recommendations, not just outcomes
02 Build trust through transparency
Explain recommendations, not just outcomes
03 Turn insights into action
Explain recommendations, not just outcomes
04 Provide guidance when it's needed
Explain recommendations, not just outcomes
05 Keep complexity behind the scenes
Explain recommendations, not just outcomes
Turning AI recommendations into confident customer conversations
We designed the experience to help teammates understand, trust, and act on AI-generated recommendations.
01 — Explain the “why”
Recommendations surface the customer signals, supporting evidence, and AI confidence behind each opportunity.
02 — Turn insight into action
Ask AI Coach helps teammates prepare for the conversation with suggested opening statements, discovery questions, and guidance for handling objections.
03 — Create a feedback loop
Teammates can provide feedback on whether a recommendation was helpful, helping improve future recommendations.
This challenge reinforced an important principle for me:
AI is most effective when it accelerates design thinking, not when it replaces it.
The final experience emerged through an iterative cycle of research, experimentation, synthesis, and refinement. AI helped us move faster and explore possibilities more efficiently, but human judgment, knowing what to prioritize, question, and refine, ultimately shaped the outcome.