Sense Space AI

Advancing Design Research Synthesis with Artificial Intelligence

Project Overview

Design research has become fragmented and time-consuming. SenseSpace emerged from recurring observation as a design manager leading big tech design teams in companies like Meta, Western Digital, Consumer Resport, PTC, and more. My designers and researchers were drowning in synthesizing many long hours of research data. Our platform cuts research processing time by 70% through intelligent automation, but more importantly, it preserves what matters – the designer’s craft. Using specific design methodologies, we’ve transformed how 50+ design teams analyze research through our secret source, leading to faster product development cycles and clearer decision-making paths.

My Role

As a design manager, I work at the intersection of AI and design, taking the role of authoring key business solutions, developing full-stack experience design for testing, and developing a cofound product team. Leveraging PhD research at Carnegie Mellon along with my role in the industry landscape as a manager, I lead the creation of a taxonomy of research methodologies spanning various design disciplines and actions, serving as SenseSpace’s unique value proposition in building core data analysis algorithms and user experience design. My focus was ensuring our automation enhanced rather than replaced human insight. I collaborated directly with researchers, Product designers, and engineers to shape both the algorithmic foundation and user experience.

Confidentiality: While key algorithms and methodological approaches remain confidential, this case study shares our core approach and what we learned from developing Sense Space

Project Duration: May - December 2024

Key Partners: Carnegie Mellon University

Team: Fas Lebbie, Spencer Allred, Hibban Butt, Mohammad Sial

Problem Context

Design research currently faces inefficiencies in the sensemaking process. Our research estimates that researchers spend up to 22 hours weekly analyzing interview data, time consumed by wrestling with analysis rather than generating actionable insights. Our discussions with product teams—including researchers, designers, and product managers—uncovered a concerning pattern: engineering teams frequently build technically sound solutions that miss user needs or create products users simply don’t want. Meanwhile, design teams propose ideas that, while appealing to users, prove technically unfeasible to implement. The core issue driving this disconnect is the gap between raw data collection and identifying meaningful patterns that can drive effective design decisions. This challenge creates a fundamental barrier in the product development process, where valuable user feedback exists but fails to translate into successful product outcomes. By addressing these inefficiencies in how teams process and interpret research data, we can bridge the gap between technical possibilities and genuine user needs, ultimately leading to products that are both technically sound and eagerly adopted by users that are done in a timely manner.

Design Interventions

Our design intervention materializes the SenseSpace app, an AI tool that streamlines the design research process by transforming how teams collect interview data and generate insights. Researchers spend up to 22 hours weekly analyzing interview data, significantly slowing down product development cycles. SenseSpace accelerates solution development by turning a week’s work into hours for design researchers. Drawing from various design methodologies, it automatically identifies patterns and generates insights. The platform combines emotional analysis through facial analysis and natural language processing to identify patterns human researchers might miss. This approach helps teams move quickly from raw data to meaningful insights, addressing the core disconnect between engineering solutions and user needs. Rather than replacing researchers, SenseSpace augments their capabilities, allowing them to focus on strategic thinking instead of manual analysis.

Researchers struggle with scattered data and disconnected tools, making it challenging to extract meaningful insights that drive impactful design decisions

Experian Onboarding screen guides users to create an account or Log in and fill in personal details for accurate credit evaluation.

Customize your experience by selecting who you'll collaborate with.

New users see a clean workspace, ready for their first project upload or draft creation.

A structured grid view organizes existing projects for easy access and management.

Multiple ways to start: conduct an interview, upload existing data, or import data.

After selecting 'Start an Interview,' define your goal and choose to begin a live recording or use an existing file."

After selecting 'Start Interview,' generate a participant link, conduct the session with live transcription, and manage the recorded interview.

Select 'Upload Your Data' to import existing text, audio, or video files for analysis.

Text-Based Interaction – User inputs text, system processes it, extracts insights, and generates a structured response.

Audio-Based Interaction – User records audio, system transcribes and analyzes it, then provides relevant insights.

Video-Based Interaction – User submits a video, system processes visuals and speech, then extracts key insights.

All Modes Combined , User integrates text, audio, and video for a comprehensive response, ensuring a well-rounded output.

Final Outcome – Regardless of input method, the system synthesizes insights and delivers a structured result.

Interface for research categorization with filtering options and highlighted insights from transcript analysis.

Analysis dashboard with text highlighting, pattern identification, and filtered research results.

Pattern recognition capabilities with yellow sticky notes representing insights extracted from research data.

Workspace with research notes, pattern visualization, and filtered results from analyzed interview data.

Multimedia analysis features showing both text insights and audio/video analysis capabilities.

Results page, export functionality, team sharing options, and project publishing workflow.

Publish interface with completed project view and publish confirmation dialog.RetryClaude can make mistakes. Please double-check responses.

Scroll to next section

My Approach

My design philosophy aims to position AI as a new raw material for designers. Instead of seeing AI as a technical tool, I focus on how it can reshape the design research process. My research aimed to improve the gap between technical capabilities and creative needs by immersing myself in designers’ workflows and challenges. This exploration highlighted the crucial gap between innovations in data science and user-centered design methodologies. My approach aims to enhance sensemaking while maintaining the intuitive craftsmanship that defines what makes design distinctly human.

Design Process

Design Research & Strategy

Our research objective was to understand how AI could enhance the design research process while exploring the divide between technical capabilities and human-centered methodologies. We interviewed over 50 design practitioners across industries, focusing on design research workflows and data collection and analysis pain points. These 60-90 minute sessions explored current research processes, challenges in sensemaking, and attitudes toward AI integration. Current sensemaking processes remain labor-intensive, with designers spending approximately 40% of project time on pattern recognition that AI could automate.

We supplemented qualitative insights with computational analysis of 200+ design research artifacts, identifying patterns in how information transforms from raw data to actionable insights. Collaborative workshops with 18 multidisciplinary teams revealed communication gaps leading to implementation failures. Working prototypes of AI-assisted research tools were tested with 25 designers, providing feedback on how AI might augment human creativity in the design research process. By mapping this landscape and understanding designers’ approaches to AI integration, we established a foundation for investigating how AI might transform the design research process.

Summary of Findings

The research revealed that designers value tools that augment their intuitive and creative processes rather than replace them. Design teams spend about 22 hours weekly on unproductive sensemaking and lose over 20 hours per project to manual analysis tasks, indicating a disconnect between data sensemaking and design intuition. This gap often results in technically sound but unusable solutions or desirable yet unfeasible ones. Our findings emphasized the need for tools that eliminate time-consuming manual work, such as generating instant interview transcripts and using them to generate insights through specific design methodologies. Discussions with researchers from institutions like Parsons School of Design and MIT highlighted the importance of utilizing design methodologies as distinct elements in grounding AI tools within design research. Participants agree that a tool embedded with specific design methodologies for researchers in gathering and sensemaking data will improve their likelihood of using it through design research tasks, provided they can validate it. We discussed employing AI to use system design tools and methods like Powers of 10, the transition design approach, and methods to interact with data transcripts. This validates the growing importance of system thinking in design research and the demand for tools supporting systematic data gathering and mapping. These insights created conditions to develop a taxonomy documenting AI capabilities across design research methodologies and web applications to help designers explore these capabilities to enhance their processes.

Prototyping & Implementation Strategy

The prototyping phase engaged 12 design researchers, 5 product managers, and five project managers from leading innovation firms like Meta, MIT, and Parsons School of Design in iterative testing sessions, shaping our development approach. Three essential components emerged as foundational for an MVP: automated interview transcription, emotional intelligence analysis, seamless integration with existing design tools, and the Validate feature, which gives researchers traceability links to where the data pipeline materialized specific insights.

Researchers unexpectedly highlighted the need for “Psycho-Portraits” – AI-generated participant profiles capturing emotional patterns and communication styles during interviews. One researcher noted, “Understanding emotional context is often more valuable than the literal transcript.” This led to the insight of developing an emotion recognition system analyzing vocal tone and facial expressions, providing deeper participant understanding. Testing revealed that 87% of researchers prioritized workflow integration over standalone functionality, such as integration with Miro and Mural, 79% valued real-time analysis during interviews, and 92% needed flexible export options for team collaboration.

Summary of Findings

Scroll to next section

Reflections & Impact

Short Term Impact

Sense Space came from repeated problems I have faced managing design teams in big tech environments. At its core, the intervention aims to reduce the time spent on tedious analysis tasks, freeing designers to focus on creative interpretation and strategic thinking. Integrating familiar design methodologies through our growing glossary of over 100 design methods and frameworks can enable designers to leverage AI-identified design opportunities that would have otherwise remained buried in transcripts, leading to more nuanced solutions.

Long Term Impact

Beyond immediate efficiency gains, this intervention begins to lay a foundational shift in how design and AI interact. By positioning AI as a new design material rather than merely a tool, we’re helping bridge the persistent gap between technical feasibility and user desirability. As AI capabilities evolve, this foundation will enable design researchers to harness increasingly sophisticated computational power while maintaining their essential human perspective.

Previous Project

All Projects

Next Project