Overview
Nectar AI is a CRM company that unifies social media messages into a single inbox. When I joined as the sole designer, the company was focused on the company focused on leveraging AI to streamline social communication for e-commerce businesses. My primary task was overhauling the existing platform, streamlining user flows, and enhancing overall user experience. The goal was to improve customer work efficiency and drive product-led growth for company.
Result
Resolved more inquiries per day, increasing productivity by
30%
Improved user satisfaction rate by
36%
Time to complete common inquires reduced by
24%
0.1 Research
During user research, I found an interesting conflict between e-commerce companies and their end customers. While e-commerce companies aim to use AI to reduce labor costs, customers prefer to speak directly with human representatives, as AI is often unable to handle complex issues effectively.
Other pain points for e-commerce company employees:
Overworked staff: 2-3 employees managing multiple social platforms
Message blindness: Focusing on one message may cause others to be overlooked.
Unclear responsibilities: No assigned ownership for message handling
High turnover: Frequent retraining required
Inefficient responses: Repetitive answers to common questions
0.2 Competitor Analysis
To understand user-familiar patterns in current solutions and identify untapped opportunities in the existing market.
Agent Side
Customer Side
03. Ideating and Defining
How might we improve our user experience?
Maintain awareness of other messages while processing one
Establish clear responsibility assignments and message status tracking
Implement AI chatbots and support templates to handle routine inquiries and automate repetitive tasks.
I ideated many ideas and then collaborated with our tech lead to devise a solution grounded in research insights, ensuring its feasibility for implementation.
04.Solution
2, Establish clear responsibility assignments and message status tracking
We redesigned the tab to help them easily find all the messages they are responsible for. Testing showed this layout is more efficient.
In the "All Messages" tab, we added name to show who is in charge of each message.
3, Use AI chatbots to respond to customer messages. Simultaneously, analyze conversation content to prioritize tasks for human representatives, ensuring a better customer experience.
AI automatically detects customer frustration through sentiment analysis and keywords, such as “answer my question”.
If urgent, AI marks the conversation “Action Required Now” to transfer to human representatives immediately. For non-urgent issues, AI marks “Waiting for Human” and continues assisting where possible.
Workflow:
1, AI automatically categorizes each incoming message (ex. product question, partnership inquiry), and responds to common questions.
2, AI flags messages needing human support as "Action Needed" or "Waiting - Non-Urgent"
3, Jess(human agent) steps in to resolve tricky conversations the AI cannot address with AI suggestions
4. Once resolved, Jess(human agent) marks messages as "Completed"
4, Implement AI support templates to help with repetitive tasks.
05. Wireframe
Sketch
Low-Fi
After testing, we switched to a three-column layout to provide more space for meaningful user purchase insights. This layout also offers more potential for future features.
High-Fi
06. User Testing
Testing the Figma prototype with 5 existing users and 5 potential customers
"The AI templates are awesome; I no longer need to manually type repetitive words."
Users can finish all tasks by themselves
9/10
"The prices and return policies vary across different platforms. I hope to differentiate them more effectively"
Avg. satisfaction rate
7.5
so…
How might we differentiate different platform effectively?
💡 What about maintain the original layout of each platform.
For Email,
For post message,
