Verdigris • sep - dec 2025 • in alpha
Chatbot to Proactive AI
Influenced product strategy and pivoted from a standalone chatbot to an AI assistant embedded in the platform data center technicians already used every day.
TIMEFRAME
2025 — 2026
ROLE
UX Research • UX Design • Prototyping • Stakeholder Management
DOMAIN
IoT • Data Center Monitoring
TEAM
Head of Product • Engineering Team
TOOLS
Figma • (add tools used)
What's Verdigris?
An IoT company whose platform helps data center technicians monitor energy use and catch anomalies in critical infrastructure before they become outages.
What was the problem?
Verdigris had built a standalone AI chatbot for technicians and brought me in to test it. Nine usability sessions showed the chatbot wasn't poorly designed, it was the wrong form entirely. It pulled technicians out of their workflow and away from the data they were asking about.
What was my impact?
9 usability sessions that changed the direction of the product. 1 recommendation against shipping — backed by evidence, accepted by leadership. Arc, the redesigned in-context assistant, now live in alpha.
CONTEXT
Verdigris makes AI sensors that detect equipment degradation in data centres before failure. They brought us in to test a chatbot prototype and determine whether it was the right product direction.
As the sole designer and one of four researchers on a sponsored project, I was brought in to run usability testing on the prototype. I led the product strategy pivot to an AI assistant embedded directly in the platform, and designed it end to end.
“We are testing this chatbot because a lot of the data centre technicians do not know what to do with the data itself. They don't know how to analyze the data. They just want the building to run efficiently.”
Jimit Shah, Head of Product @ Verdigris
problem
The AI had the knowledge. The interface expected users to know how to use it. The last mile from warning of to response was broken.
The chatbot required technicians to interpret raw electrical data, know what questions to ask, and then figure out what to do all on their own. It described problems. It didn not help solve them. And because it lived outside the platform they worked in, every conversation started from zero.
solution
We embedded a context-aware AI assistant directly into the dashboard technicians were already using every day.
The chatbot required technicians to interpret raw electrical data, know what questions to ask, and then figure out what to do all on their own. It described problems. It didn not help solve them. And because it lived outside the platform they worked in, every conversation started from zero.
Contextual
Trustworthy
Proactive
Confident
Arc
01 / 05
Push notifications that proactively alert technicians
Goal is for technicians to be alerted if something is going wrong. Entry point being lockscreen instead of a chat text box allows for one tap to act. Push notification eliminates the blank-prompt problem entirely.
research
The chatbot failed to pique the interest of data center technicians because it added friction to their process and did not help them.
We ran moderated usability tests with 9 technicians and contextual inquiries with 2 data centre technicians to identify their daily workflows and surface their needs.
Glanceability
8/9 participants
Dense text, no hierarchy, technicians could not scan while standing at a panel.
Actionability
8/9 participants
The chatbot surfaced problems without advising on what to do with the data.
Trust
9/9 participants
Most participants were not AI savvy, did not trust the data and asked for its source.
Focus
9/9 participants
Blank prompt, open-ended chat interface. Technicians didn't know what to ask.
jobs to be done
What technicians and energy managers actually need from AI.
Triage
When I'm between buildings, I need to see which ones need attention right now so I can respond to the most urgent issue first.
Diagnose + Act
When the AI flags an anomaly, I need to know what's wrong, its seriousness, and what to do so I can fix it without interpreting raw data.
Hand Off
When my shift ends, I need to pass context to the next operator so they can pick up where I left off without starting over.
THE PIVOT
As the sole designer, I replaced the chatbot with a proactive, notification-first alert system.
AI can predict when systems fail but the chat interface waits for the right query to surafce that, making poor use of the technology.
Our research showed that data center technicians are in fast-paced highs stakes conditions, on iPads/ phones + they are not electrical engineers with the knowledge to read dashboards and analyze next steps. They need a tool to analyze dashboards quickly and surface next steps.
User types a question into a chatbot
App sends a push notification when something goes wrong
Desktop-only dashboard
iPad and phone app for operators in the field.
Open-ended text box with no starting point
Chat only opens for one specific alert at a time.
AI gives answers with no source
Every answer shows which sensor, what time windoW + a confidence %.
Tells you what's wrong, then stops
Tells you what's wrong, suggests a fix, and lets you schedule it.
Impact & Reflection
Arc is now in alpha. The most valuable thing I designed on this project was the recommendation not to ship.
Research is only useful if it can change the plan. This project taught me how to turn 9 sessions of evidence into a decision leadership could stand behind and how to pair a "no" with a better path forward.
Not every AI product needs to be conversational.
The AI already knew what was wrong. But, the technicians did not know its capabilities, which was hiding behind the right query, waiting to be asked.
The best AI interface is the one the user never has to learn.
We framed it as avoiding costly misalignment rather than invalidating their work. The AI layer is still there it moved from the interaction surface to the intelligence layer underneath.
Research is most powerful when it changes the direction, not just the design.
Our findings didn't improve the chatbot. It convinced Verdigris not to ship it. That's the more honest outcome and the more valuable one.