AI Reviews Summary
Lead Product Designer.
This feature began as an idea I pitched to the team :)
Hypothesis
Reviews exist to reduce uncertainty, but shoppers don't have time to read through hundreds of them. What if AI could instantly summarize hundreds of reviews into the key insights shoppers actually care about?
The challenge
At Yotpo, I worked on the Reviews product, where one of the biggest challenges was finding a meaningful way to innovate in a mature, highly competitive market. Rather than asking "what new reviews feature can we build?", I reframed the problem.
How might we help shoppers make faster, more confident purchase decisions?
Proof of concept
To validate the idea quickly, I built a simple proof of concept using ChatGPT, feeding a top merchant's customer reviews into it and generating a concise summary of key insights. It demonstrated the potential clearly enough to win strong support from the team and leadership, becoming the foundation for further exploration.
Discovery & research
Before designing, I needed to validate one core assumption: would an AI-generated summary actually help shoppers decide faster, while still feeling trustworthy? Since the feature served two audiences, research covered both — usability testing with shoppers to understand how they read reviews and what builds (or breaks) trust in AI-generated content, and validation with merchants, who ultimately decide whether to display the summary on their product pages.
KEY INSIGHT - SHOPPERS
Transparency
Shoppers wanted to understand how the summary was generated and what it was based on.
KEY INSIGHT - SHOPPERS
Reliability
Balanced summaries felt more trustworthy than overly positive ones.
KEY INSIGHT - MERCHANTS
Confidence
Merchants needed assurance the summary accurately reflected their customers' reviews.
KEY INSIGHT - merchants
Control
Merchants wanted flexibility in how the summary was presented on their storefront.
Core challenges
If shoppers questioned the summary, the feature would fail regardless of how accurate the AI actually was.
How might we help shoppers verify the source behind each summarized insight, without forcing them to read every review?
APPROACH
Each summarized topic became interactive — clicking it jumped shoppers directly to the reviews behind that insight, exposing the evidence instead of asking them to blindly trust the AI.
User-generated content is rarely black and white, and conflicting opinions are often what make reviews valuable.
How might we summarize hundreds of reviews while preserving the diversity and nuance of customer feedback?
APPROACH
This couldn't be solved through interface design alone. I worked closely with the Data Science team to define principles that kept summaries faithful to the original reviews — representing overall sentiment while surfacing both positive and negative feedback.
Merchants were excited by the innovation but wary of an AI element competing with their existing page hierarchy.
How might we make the feature discoverable & valuable without overwhelming the product page?
APPROACH
I explored a gated reveal (summary appears only after shoppers interact with reviews) and a banner treatment. The gated version reduced clutter but hurt discovery; the banner improved visibility but felt too promotional. Both iterations shaped a more integrated final placement.
Design process
To validate the design, I conducted usability sessions with potential shoppers, testing multiple versions of the Review Summary.
The goal was to understand which information users naturally gravitated toward, what they considered most valuable, and which layout was the easiest to scan and understand. I explored a wide range of approaches, including an early ChatGPT-inspired design, familiar star-rating patterns, different information hierarchies etc. The insights from these sessions guided the evolution of the feature and helped shape a design that felt both intuitive and trustworthy.
Final design
PositioningThe summary lives in two places: the header of the reviews section, and next to the star rating where shoppers first encounter review counts, both editable by merchants.
InteractionThe summary opens in a thin drawer with a slight page darkening, keeping shoppers oriented while letting them explore the summary.
Trust was built into every layer of the experience.
Familiar anchors, such as the overall rating and review count, connected the summary to elements shoppers had already seen on the page, reinforcing continuity and credibility. To keep the experience easy to scan, I intentionally surfaced only a small set of the most representative insights rather than every theme found in the reviews.
Usability testing also showed that adding a subtle sentiment icon next to each topic significantly improved comprehension, allowing shoppers to quickly distinguish positive, negative, and mixed insights before reading further.
Outcome
with the summary
with adoption still growing
Key learnings
- 1. Trust is everything in AI experiences.Building trust meant connecting the human element with the AI-generated output — making the technology feel transparent, reliable, and aligned with merchant expectations.
- 2. New technology means balancing multiple stakeholders.Merchants, shoppers, and business goals didn't always align, so I worked closely with top merchants to build confidence and give them real control over the experience.
- 3. Designing AI features means designing the output, not just the interface.The quality, structure, and tone of the generated summary was as much a design decision as the UI presenting it.