anylytics.ai
Anylytics.AI, an upcoming startup that houses and interprets complex data scopes for businesses, needed an interactive, intuitive, and social AI chatbot feature for their platform.
As a lead designer, I was tasked with building an interactive chatbot that could simplify complex data insights without overwhelming users.
What is Anylytics about?Anylytics wants to make data interpretation easier for both excel warriors and data newbies, as they cater to businesses in a variety of industries. The goal is to democratize data analytics in the current market!
I conducted three quick interviews with a crystal report analyst, consultant, and product manager to understand user pain points with current data analytics and AI tools on the market. Here’s what I found...
Interviewees who had experience with tools like JuliusAI and Microsoft Power BI expressed that while there were a variety of useful data analytic tools, there was a steep learning curve for beginners.
There seemed to be a general lack of customization for data visualizations and interfaces, often making products fall short of specific business needs.
People also had a desire to see multiple data insights within one seamless interface, and understand the technical context of their data.
With this in mind, I went into the design process focusing on both users new to data analytics and those with more experience.
*Another feature I focused on in initial designs was the ability to share conversations between employees. Although not implemented into the final MVP, I really enjoyed working on it.
Initial designs aimed to empower users to generate graphs and tables, switch between data scopes, and share data between teams.
I introduced tabs to simulate a familiar user experience that would let them easily switch between data scopes.
The interface felt crowded and lacked clear action paths after the copilot provided data.
Users need a more direct way to switch between data sets, as this was a central component of the user experience.
“Users will feel lost among all the tools”
Notes + feedback from the product team led me to revisit how the workspace reflected AI generated insights + the relationships between data scopes and connections that are present throughout the rest of the product.
How can micro-components (touchpoints, dropdowns) clarify this system?
A lot of my work from here on out was refining + developing micro-components within the interface. The general design was there, and due to quick shipping timelines, couldn’t undergo much change. However, smaller interactions within the interface were undefined, and didn’t provide enough context for the data. Here are a few things I was developing over rounds of revision: data scope switching, conversation filtering, and clarifying feature functionality.
To reduce clutter, I introduced collapsible navigation and sidebars, and added feature icons (sharing, visualizations, MySQL code generation) to make advanced features more accessible without overwhelming users.
I also added conversation filtering + visible scope switching, to allow users to access scopes outside of conversation tabs and easily parse through past conversations, adding more context for data insights.
Additionally, for more hesitant users, I implemented confirmation states, to make the user experience less anxiety inducing!
Testing also showed a decrease in task completion time from the initial design.
In a market increasingly reliant on AI tools, it’s hard to stand out as a competitor. For Anylytics.AI, this meant putting the user first, and prioritizing an experience that businesses want to come back to.
As a designer, this project provided me an opportunity to think about data accessibility, and how we as developers, designers, and engineers can make the technical world more friendly for all. (: