Chromascribe
Chromascribe
Making transcript analysis easier to navigate
Making transcript analysis easier to navigate
Summary
Summary
Chromascribe is an AI-assisted qualitative analysis tool for researchers working with large sets of interview transcripts. I helped turn an older prototype into a research-ready web product by rebuilding core parts of the tool, improving transcript navigation, and shaping implementation-aware UX decisions.
Chromascribe is an AI-assisted qualitative analysis tool for researchers working with large sets of interview transcripts. I helped turn an older prototype into a research-ready web product by rebuilding core parts of the tool, improving transcript navigation, and shaping implementation-aware UX decisions.
Stack
Stack
Figma, Python, HTML/CSS, D3.js, Render
Figma, Python, HTML/CSS, D3.js, Render
The product was informed by
The product was informed by
15+ interviews,
3 focus groups, and testing with
22 participants.
15+ interviews,
3 focus groups, and testing with
22 participants.
In evaluation, the broader workflow was associated with a
In evaluation, the broader workflow was associated with a
48% increase in data discovery speed and a
56% reduction in analysis time.
48% increase in data discovery speed and a
56% reduction in analysis time.
Context
Context
The Problem
The Problem
Qualitative research becomes hard to manage when teams are working across many transcripts, many participants, and overlapping themes.
Researchers need to move between excerpts, codes, themes, and comparisons quickly, but most workflows make that slow and fragmented.
Qualitative research becomes hard to manage when teams are working across many transcripts, many participants, and overlapping themes.
Researchers need to move between excerpts, codes, themes, and comparisons quickly, but most workflows make that slow and fragmented.
Chromascribe was designed to make that process easier by combining AI-assisted coding with transcript visualization and structured navigation.
Chromascribe was designed to make that process easier by combining AI-assisted coding with transcript visualization and structured navigation.
Why this mattered
Why this mattered
This was not just a transcript viewer. The product needed to support a real analysis workflow: reviewing transcripts, managing codes, comparing participants, and finding patterns without getting lost in the data.
That meant the interface had to do two things well:
Support detailed reading
Help researchers zoom out and compare patterns across a larger dataset
This was not just a transcript viewer. The product needed to support a real analysis workflow: reviewing transcripts, managing codes, comparing participants, and finding patterns without getting lost in the data.
That meant the interface had to do two things well:
Support detailed reading
Help researchers zoom out and compare patterns across a larger dataset
Role
I worked as a developer and UX contributor on a team with my professor, two UX researchers/designers, and two other developer.
I worked as a developer and UX contributor on a team with my professor, two UX researchers/designers, and two other developer.
Contributions
Cleaning and rebuilding the older web tool
Implementing search in visualization mode and adding a question-based transcript view
Helping shape layout and screen structure with the UX team and supporting usability testing
Leading the dev team
Cleaning and rebuilding the older web tool
Implementing search in visualization mode and adding a question-based transcript view
Helping shape layout and screen structure with the UX team and supporting usability testing
Leading the dev team
The workflow
Starting with a tool that was not ready for testing
Before we could learn from researchers, the product needed to be stable and usable enough to test. I started by cleaning up the older web tool, improving the codebase, and hosting it live so the team could run remote studies and focus groups.
That work was important because it moved the project from concept territory into something researchers could actually interact with.
Making large transcript sets easier to scan
One of the biggest workflow improvements I implemented was around transcript navigation. I contributed in adding:
The question-based view made it easier to compare responses across participants without forcing researchers to read every transcript linearly. Instead of digging through full conversations one by one, they could move directly into grouped responses around the same prompt.
Designing for comparison, not just reading
A key part of Chromascribe’s value was helping researchers compare patterns across data, not just read one transcript at a time.
To support that, the product used a timeline-like visualization with color-coded themes across participant rows. This gave researchers a higher-level way to scan where themes appeared, then drill into transcript details when needed.
Because I was implementing the product directly, I was also able to work closely with the UX team on layout and element placement, helping balance researcher needs with what was realistically achievable in the interface.
The workflow
Starting with a tool that was not ready for testing
Before we could learn from researchers, the product needed to be stable and usable enough to test. I started by cleaning up the older web tool, improving the codebase, and hosting it live so the team could run remote studies and focus groups.
That work was important because it moved the project from concept territory into something researchers could actually interact with.
Making large transcript sets easier to scan
One of the biggest workflow improvements I implemented was around transcript navigation. I contributed in adding:
The question-based view made it easier to compare responses across participants without forcing researchers to read every transcript linearly. Instead of digging through full conversations one by one, they could move directly into grouped responses around the same prompt.
Designing for comparison, not just reading
A key part of Chromascribe’s value was helping researchers compare patterns across data, not just read one transcript at a time.
To support that, the product used a timeline-like visualization with color-coded themes across participant rows. This gave researchers a higher-level way to scan where themes appeared, then drill into transcript details when needed.
Because I was implementing the product directly, I was also able to work closely with the UX team on layout and element placement, helping balance researcher needs with what was realistically achievable in the interface.
Turning feedback into product changes
Turning feedback into product changes
The product was refined through multiple rounds of research and usability feedback. Across the broader project, the team ran 15+ interviews, 3 focus groups, and mixed-methods testing with 22 participants, identifying 6 usability barriers across 3 design iterations.
My work supported that loop by turning feedback into product changes, especially around navigation, structure, and the readability of transcript workflows.
The product was refined through multiple rounds of research and usability feedback. Across the broader project, the team ran 15+ interviews, 3 focus groups, and mixed-methods testing with 22 participants, identifying 6 usability barriers across 3 design iterations.
My work supported that loop by turning feedback into product changes, especially around navigation, structure, and the readability of transcript workflows.
Focus Group
Identified issues & needs
Design Changes
Usability Testings
Usability Testings
Outcomes
Outcomes
Chromascribe became a live, research-ready web tool that could support remote studies and focus groups.
Chromascribe became a live, research-ready web tool that could support remote studies and focus groups.
At the team level, the evaluated workflow was associated with:
At the team level, the evaluated workflow was associated with:
48%
48%
faster data discovery
faster data discovery
56%
56%
lower analysis time
lower analysis time
What this project proves
This project shows how I work best: in complex, ambiguous spaces where product thinking, UX, research, and implementation all shape each other. It also shows that I can help turn a technically complex concept into a usable product by bridging design intent and build reality.
This project shows how I work best: in complex, ambiguous spaces where product thinking, UX, research, and implementation all shape each other. It also shows that I can help turn a technically complex concept into a usable product by bridging design intent and build reality.
Reflection
Reflection
Chromascribe pushed me to design for expert workflows rather than lightweight interfaces. It strengthened my ability to make dense systems easier to navigate, collaborate across research and design disciplines, and contribute with ownership when a project is still evolving.
If I were continuing the work, I would explore clearer AI confidence patterns, better code/theme discoverability, and even stronger comparison flows across transcripts.
Chromascribe pushed me to design for expert workflows rather than lightweight interfaces. It strengthened my ability to make dense systems easier to navigate, collaborate across research and design disciplines, and contribute with ownership when a project is still evolving.
If I were continuing the work, I would explore clearer AI confidence patterns, better code/theme discoverability, and even stronger comparison flows across transcripts.
View other projects
View other projects
Let’s Connect
To collaborate and solve bigger problems
Contact me
Let’s Connect
To collaborate and solve bigger problems
Contact me
Let’s Connect
To collaborate and solve bigger problems
Contact me