Quick Commerce with AI assistant - Case Study
AI shopping assistant to support customer purchases online for quick commerce platform to efficiently give suggestions and recommendations for users to make more informed and faster decisions.
Role
UX/UI Designer
Industry
Quick Commerce
Duration
1 month



User Testing & Iterations
Organized a series of remote user testing sessions to evaluate the AI feature integration of a quick commerce platform's usability and effectiveness in fostering collaborative learning. Analyzed feedback to identify patterns and areas for improvement, leading to several design iterations that enhanced user engagement and satisfaction.
Learn if the users are able to identify the AI assistant in the quick commerce platform
Learn if they are able add items from the chat
Learn if the users are able easily navigate around different screens.
Find out how satisfied participants are with the app.
Task assigned:
Find the AI assistant.
Add an item of your choice for checkout
If you are not sure with something, how you going to seek help?
Find out how satisfied participants are with the app.
The prototype test done on 4 participants were moderated keeping in mind timeline constraints I had. Main goals were as following.
Key takeaways:
All the participants were able to complete the tasks.
1 participant had doubts finding what they wanted in the prompt initially, but made it through once they got familiar with the flow
Everyone was able to navigate easily through all the screens and access the help section.
One suggested we might even have a curated list of items with the help of AI to add to cart based on their region and timely purchase patterns



Next Steps & Learning Outcomes:
The AI feature holds strong potential to be expanded further by leveraging user purchase patterns and contextual data to deliver even more relevant, time-saving suggestions. The next step will be to incorporate insights gathered during user testing into the current design and conduct another round of validation to assess improvements. This process will be iterative refine, test, learn, and repeat until the assistant becomes both intuitive and reliable in aiding faster decision-making.
Prepared an in-depth presentation and comprehensive documentation detailing the research findings, design rationale, user testing outcomes, and the iterative design process. Highlighted the app's potential to transform the educational landscape by making learning more interactive, engaging, and collaborative.
What Did I Learn?
Gained a deep understanding of how user needs and behaviors vary across different age groups, which influenced design decisions around layout, text size, and navigation.
Direct feedback from user testing sessions provided valuable insight into pain points and usability issues.
Several screens went through multiple design iterations, and peer design reviews at each stage helped guide the final outcome.
Developed a strong awareness of accessibility principles, particularly in creating inclusive interfaces that accommodate users of all abilities and experience levels.
What Would I Do Differently?
Given more time, I would have expanded the design scope to include a more complete set of screens and edge cases, building a fuller product narrative.
I would also prioritize early-stage testing, even at the low-fidelity stage, to catch usability issues before investing time in high-fidelity design.
Incorporating more cross-functional feedback earlier in the process from developers and product stakeholders would have helped align expectations and reduce rework.

Other projects

Optra AI - Interactive Dashboard
AI powered system that helps manufacturing supervisors monitor machine performance in real time and assign the right workers to the right tasks for smoother, more efficient plant operations.

Aloha Cloud POS
Shaping next generations POS experiences

Designer's Workspace
Reimagining Designer's workspace through ergonomic lens








