Skip to main content
Nila Gao
← Back to projects

Case study · Athenic AI

Data XRay

Athenic lets business teams analyze data in plain English — no SQL, no data team required. I led the end-to-end design to make that promise feel real.

Data XRay cover
Company
Athenic AI
Focus
AI UX · Activation · Engagement
Impact
+18% activation · BMW as customer

Background

Powerful AI. But nobody could use it.

Users would sign up, get confused, and leave before experiencing any value. Not because the AI failed — because the experience got in the way.

Unclear question asking
Users didn't know how to phrase questions the AI could actually answer.
Hidden product value
Users couldn't see enough of the product to understand what was possible.
No continuity
Every session felt like starting over — no history, no follow-ups, no flow.
Fragmented flows
Dashboard and search were disconnected — constant context switching.
Understanding pain points

Design thinking

Fewer features. More clarity.

Rather than adding more AI power, I focused on instructional design, discoverability, and conversational continuity. I led a whiteboard session with engineering to map capabilities and prioritize what to build first.

Whiteboard session

Over 12 rounds of user testing, I iterated through four distinct product directions before converging on the workbook.

V1
Search bar
Asking AI questions for tables & graphs
V2
Chat
Transition from search to conversational AI
V3
Tabs
Reducing clutter through merged navigation
V4 · chosen
Workbook
Merging search and dashboard into one unified space
Iteration studies
Search bar
Search bar experience
Asking AI questions for tables & graphs
Chat
Chat experience
Transition from search AI to conversational AI
Tabs
Tabs experience
Reducing clutter through merged tabs
Workbook
Workbook experience · chosen
Merging search and dashboard into one unified space
Key insight
Users didn't need more analytical power — they needed clarity, guidance, and continuity. The constraint wasn't the AI. It was the experience around it.

Final design

Ask. See. Remember.

Chat, charts, and saved insights unified in one workbook. Users ask a question, see the answer visualized, and build on it — without ever losing their place.

Workbook & chat — unified experience

Unified workbook
Ask questions and see charts in one place — no context switching between search and dashboard.

Question asking — transparency during wait time

Transparent wait time
Animated feedback while the backend processes — pulls tables first, then graphs, showing where data comes from. Builds trust while users wait.

Question history — continuity across sessions

Question history
Access previously asked questions within the current session and across past sessions — so insights build on each other instead of starting over every time.

Impact

Results

+18%
Increase in product activation
15
Installs in the first week post-launch
BMW
Enterprise customer acquired
Reflection
Powerful AI is only valuable when users understand and trust it. By reframing analytics as a conversational, insight-driven experience, Data XRay helped non-technical teams engage with their data confidently — without needing a data analyst in the room.
↑ Back to top