COMPANY
PRODUCT
Available to registered business users only.
ROLE
TIMELINE
TEAM
1 Chief Engineer
4 Engineers
TOOL
Figma
OVERVIEW
As the sole UI/UX Designer on CPII's AI team, I transformed ChatDoc Master from an internal research tool into a market-ready B2B AI-powered chatbot builder. The redesigned tool successfully launched, empowering businesses to create and adopt AI-driven chatbots with ease.
PROBLEM
ChatDoc Master began as a research tool to evaluate LLMs' retrieval and question-answering capabilities. As AI chatbots gained traction in the business world, our team saw an opportunity to evolve it into a B2B product. But before we could enter the market, I needed to bridge the usability gap.
OLD DESIGN OF CHATDOC MASTER
USABILITY ISSUES
01
Limited to single-source uploads
02
No customization or update options
03
Excessive scrolling due to linear layout
SOLUTION
I designed a tabbed interface that allows users to upload multiple data sources within a single workflow, addressing business users’ need to work with varied and multiple files.
I introduced customization options to give users the autonomy to tailor chatbots to their specific business needs.
Before Generation: Customize chatbot functionality
After Generation: Personalize the messaging elements
Clickable citations let users trace each answer back to its original source with one click, reinforcing trust and aligning with user expectations for accountable AI.
Users can update chatbots by adding or removing sources, ensuring content stays accurate over time without needing to rebuild the bot from scratch.
I designed a collapsible sidebar to let users quickly find and switch between chatbots, streamlining chatbot management without cluttering the interface.
RESEARCH
I interviewed seven early business users who had tried ChatDoc Master through free trials to uncover user pain points. I then translated them into design opportunities.
01
The single-source upload limit frustrated business users who often needed to work with multiple files.
"We have reports, FAQs, and support articles. It’s frustrating when we can’t upload everything at once."
User quote
Support multi-source uploads
02
Businesses had to regenerate a chatbot every time they updated the data source.
"Our website updates monthly. Having to rebuild the entire chatbot each time isn't sustainable for us."
User quote
03
Businesses faced challenges managing multiple chatbots.
71%
of users struggled with parallel chatbot generation
20s
required for users to locate an existing chatbot
By conducting a competitive analysis, I aimed to identify features competitors offered that we did not to close critical gaps, and to surface unmet needs that ChatDoc Master could address to stand out. With limited technical resources, I prioritized features that were low-effort, high-impact for our MVP.
OPPORTUNITY
IDEATION
This diagram outlines the redesigned end-to-end journey: from initial chatbot creation to customization, deployment, and updates, with the five core features integrated (highlighted in the flow).
IMPACT
To evaluate whether the redesign resolved pain points from the old design and validate new features, I conducted usability testing with 14 users—half testing the old design and half testing the new design.
TAKEAWAYS
Working full-time in a fast-paced startup environment challenged me to grow not only as a designer, but also as a communicator and problem-solver.
Designing AI tools required making complex technology accessible. Taking the time to understand the technical concepts myself enabled me to present information in user-friendly language that caters to users with varying levels of expertise.
Throughout the design lifecycle, I maintained open communication with the development team to validate technical feasibility. This proactive collaboration ensured design-to-development alignment, allowing me to address potential issues early through quality assurance.
In a startup environment, constraints became opportunities for creativity. This experience taught me to find creative solutions while balancing user needs, technical feasibility, and business realities.
A big thank you to my team :)
