international motors
synthesizing
human insight
at scale
How I use AI as a collaborative partner in user research
international motors
synthesizing
human insight
at scale
How I use AI as a collaborative partner in user research
international motors
synthesizing
human insight
at scale
How I use AI as a collaborative partner in user research
This is what research looks like when it works.
When dealer feedback piled up and timelines tightened, I used AI to help me cut through the noise. What started as a messy mix of transcripts and surveys became a strategic insight engine—powering design decisions with clarity, empathy, and speed.
Role: Lead UX , Commercial Sales Dealer Experience
This is what research looks like when it works.
When dealer feedback piled up and timelines tightened, I used AI to help me cut through the noise. What started as a messy mix of transcripts and surveys became a strategic insight engine—powering design decisions with clarity, empathy, and speed.
Role: Lead UX , Commercial Sales Dealer Experience
This is what research looks like when it works.
When dealer feedback piled up and timelines tightened, I used AI to help me cut through the noise. What started as a messy mix of transcripts and surveys became a strategic insight engine—powering design decisions with clarity, empathy, and speed.
Role: Lead UX , Commercial Sales Dealer Experience
The Challenge
As a Lead UX Designer, I’m constantly navigating the space between product ambition and user reality. In one recent project, we were redesigning a proposal generation tool used by commercial truck and bus dealers. The stakes were high: legacy systems were slowing down sales, dealers were frustrated, and internal teams were eager for a polished solution.
But we had a problem—too many fragmented inputs.
I was sitting on a mountain of dealer feedback sessions, interview transcripts, quantitative surveys, and internal assumptions. What we didn’t have was clarity. There wasn’t time for a traditional research synthesis cycle. We needed fast, actionable insight without sacrificing depth or integrity.
The Challenge
As a Lead UX Designer, I’m constantly navigating the space between product ambition and user reality. In one recent project, we were redesigning a proposal generation tool used by commercial truck and bus dealers. The stakes were high: legacy systems were slowing down sales, dealers were frustrated, and internal teams were eager for a polished solution.
But we had a problem—too many fragmented inputs.
I was sitting on a mountain of dealer feedback sessions, interview transcripts, quantitative surveys, and internal assumptions. What we didn’t have was clarity. There wasn’t time for a traditional research synthesis cycle. We needed fast, actionable insight without sacrificing depth or integrity.
The Challenge
As a Lead UX Designer, I’m constantly navigating the space between product ambition and user reality. In one recent project, we were redesigning a proposal generation tool used by commercial truck and bus dealers. The stakes were high: legacy systems were slowing down sales, dealers were frustrated, and internal teams were eager for a polished solution.
But we had a problem—too many fragmented inputs.
I was sitting on a mountain of dealer feedback sessions, interview transcripts, quantitative surveys, and internal assumptions. What we didn’t have was clarity. There wasn’t time for a traditional research synthesis cycle. We needed fast, actionable insight without sacrificing depth or integrity.
The Opportunity
This is where I brought in my AI partner—not as a shortcut, but as a collaborator.
I’ve spent the last year experimenting with how AI can meaningfully support UX strategy. My approach blends human empathy and interpretation with machine speed and structure. For this project, I used AI to help me:
Transcribe and scan user interviews for recurring patterns
Generate a taggable codebook based on both qualitative and quantitative inputs
Score each insight for impact and business ROI
Visualize findings in the form of decks, matrices, and executive briefs
The Opportunity
This is where I brought in my AI partner—not as a shortcut, but as a collaborator.
I’ve spent the last year experimenting with how AI can meaningfully support UX strategy. My approach blends human empathy and interpretation with machine speed and structure. For this project, I used AI to help me:
Transcribe and scan user interviews for recurring patterns
Generate a taggable codebook based on both qualitative and quantitative inputs
Score each insight for impact and business ROI
Visualize findings in the form of decks, matrices, and executive briefs
The Opportunity
This is where I brought in my AI partner—not as a shortcut, but as a collaborator.
I’ve spent the last year experimenting with how AI can meaningfully support UX strategy. My approach blends human empathy and interpretation with machine speed and structure. For this project, I used AI to help me:
Transcribe and scan user interviews for recurring patterns
Generate a taggable codebook based on both qualitative and quantitative inputs
Score each insight for impact and business ROI
Visualize findings in the form of decks, matrices, and executive briefs
Instead of spending days manually sorting through notes and sticky tags, I was able to focus my energy on defining what mattered—and building a compelling story from it.
Instead of spending days manually sorting through notes and sticky tags, I was able to focus my energy on defining what mattered—and building a compelling story from it.
Instead of spending days manually sorting through notes and sticky tags, I was able to focus my energy on defining what mattered—and building a compelling story from it.
What We Uncovered
Through this hybrid process, we identified 13 recurring feedback themes, ranging from image customization and spec inaccuracies to confusing terminology and session timeouts.
Then we layered in dealer interviews, survey metrics, and additional user feedback, scoring each insight based on:
Impact to user workflow
Potential business value
Priority index for the roadmap
Some of the top findings included:
Proposal Build Time – taking too long, too fragmented
Editability + Custom Forms – high demand, high payoff
Spec Accuracy + Visibility – critical for credibility
User Flow Inefficiency – minor frustrations compounding over time
What We Uncovered
Through this hybrid process, we identified 13 recurring feedback themes, ranging from image customization and spec inaccuracies to confusing terminology and session timeouts.
Then we layered in dealer interviews, survey metrics, and additional user feedback, scoring each insight based on:
Impact to user workflow
Potential business value
Priority index for the roadmap
Some of the top findings included:
Proposal Build Time – taking too long, too fragmented
Editability + Custom Forms – high demand, high payoff
Spec Accuracy + Visibility – critical for credibility
User Flow Inefficiency – minor frustrations compounding over time
What We Uncovered
Through this hybrid process, we identified 13 recurring feedback themes, ranging from image customization and spec inaccuracies to confusing terminology and session timeouts.
Then we layered in dealer interviews, survey metrics, and additional user feedback, scoring each insight based on:
Impact to user workflow
Potential business value
Priority index for the roadmap
Some of the top findings included:
Proposal Build Time – taking too long, too fragmented
Editability + Custom Forms – high demand, high payoff
Spec Accuracy + Visibility – critical for credibility
User Flow Inefficiency – minor frustrations compounding over time
Deliverables I Created
Using this research-AI pairing, I was able to generate:
A prioritized insight synthesis doc
Codebook with tags, definitions, quotes, and survey links
Persona journey and empathy map
Executive one-pager and presentation-ready deck
A roadmap-ready prioritization matrix (based on insight scores)
All of this was grounded in real voice-of-user data, structured clearly, and delivered in a fraction of the usual time.
Deliverables I Created
Using this research-AI pairing, I was able to generate:
A prioritized insight synthesis doc
Codebook with tags, definitions, quotes, and survey links
Persona journey and empathy map
Executive one-pager and presentation-ready deck
A roadmap-ready prioritization matrix (based on insight scores)
All of this was grounded in real voice-of-user data, structured clearly, and delivered in a fraction of the usual time.
Deliverables I Created
Using this research-AI pairing, I was able to generate:
A prioritized insight synthesis doc
Codebook with tags, definitions, quotes, and survey links
Persona journey and empathy map
Executive one-pager and presentation-ready deck
A roadmap-ready prioritization matrix (based on insight scores)
All of this was grounded in real voice-of-user data, structured clearly, and delivered in a fraction of the usual time.
Reflections
This project wasn’t just about streamlining research—it was about scaling insight.
What I’ve learned is this: AI doesn’t replace research. It amplifies it.
It helps me see patterns faster, make connections across data types, and spend more time asking the right questions. My role is still deeply human—listening, interpreting, validating. But with AI, I’m able to move faster and frame insights more strategically.
It’s changed the way I work—and how I show up as a design leader.
What’s Next
I’m continuing to explore how AI can support:
Insight dashboards for ongoing feedback loops
Predictive tagging based on user segments
Auto-generated journey maps and job-to-be-done modeling
I am also currently doing a lot of experimentation with training GPTs as virtual think teams for better checks and balances.
Whether I am using AI as a collaborator, or not, it’s still the same goal: connect to the user, uncover what matters, and turn insight into action.
Shaping the Future of EV Experiences
Learn how I blended psychology, systems thinking, and UX craft to shape sustainable EV experiences.
Shaping the Future of EV Experiences
Learn how I blended psychology, systems thinking, and UX craft to shape sustainable EV experiences.
Shaping the Future of EV Experiences
Learn how I blended psychology, systems thinking, and UX craft to shape sustainable EV experiences.