Projects
GigSense
An LLM-Infused Tool for Workers’ Collective Intelligence
.png)
Collective intelligence among gig workers yields considerable advantages, including improved information exchange, deeper social bonds, and stronger advocacy for better labor conditions. Especially as it enables workers to collaboratively pinpoint shared challenges and devise optimal strategies for addressing these issues. However, enabling collective intelligence remains challenging, as existing tools often overestimate gig workers’ available time and uniformity in analytical reasoning. To overcome this, we introduce GigSense, a tool that leverages large language models alongside theories of collective intelligence and sensemaking. GigSense enables gig workers to rapidly understand and address shared challenges effectively, irrespective of their diverse backgrounds. Our user study showed that GigSense users outperformed those using a control interface in problem identification and generated solutions more quickly and of higher quality, with better usability experiences reported. GigSense not only empowers gig workers but also opens up new possibilities for supporting workers more broadly, demonstrating the potential of large language model interfaces to enhance collective intelligence efforts in the evolving workplace
Working Papars
How can we co-design generative AI tools with gig workers to enhance their collaborative process and foster a community of practice in knowledge gig work, while addressing ethical considerations and ensuring inclusivity in the design process?
1. Modeling the Interaction of Visually Impaired Developers with Code Recommendation System
​
How can AI code recommendation tools like GitHub Copilot be optimized to enhance accessibility and usability for visually impaired developers, and what specific design modifications and features are needed to align these tools with the unique needs and workflows of programmers with visual impairments?
​
2. Beyond Individual Productivity: Reimagining Generative AI for Knowledge Gig Worker Collaboration
3. Building Adaptive Learning Experience for Non-Traditional and Diverse Learners for Workforce Reintegration
How can AI-driven adaptive learning systems be designed to facilitate workforce development in the digital economy, with a focus on supporting non-traditional learners' skill acquisition and career transitions?
Undergradute Projects
Majdoors
Online Platform for Digitalizing Construction Gig Workforce of India
Founder and Project Head, Undergraduate Thesis
The COVID-19 pandemic and the subsequent lockdowns had a significant impact on the lives of millions of people around the world, including migrant construction workers in India. In response to this crisis, I founded Majdoors, an online gig platform aimed at addressing the digital disparity among blue-collar workers in the construction industry.
​
Majdoors is a socio-economic upliftment project that aims to reduce the gap between blue-collar workers and clients by connecting them directly on a digital platform.
​
Majdoors has successfully reconnected more than 500 blue-collar workers with employers who were jobless during the COVID-19 lockdown. The platform has also built a network of over 800 workers from 120+ districts across 7 Indian states, providing a much-needed source of income for many families.
Connection-Aid
UX Researcher at Ministry of Health, Govt of Delhi
Substance abuse is a major public health issue that affects millions of people globally. In response to this problem, I led a product team to design a mobile app that provides support for compassionate user groups. We also performed data analysis to estimate the support system needed for recovered teenagers.
One key feature of this initiative is a mobile app designed to monitor and prevent relapse in teenagers recovering from addiction. The app uses randomized control trials to track behavior patterns and provide tailored support to those at risk of relapse. This app serves as a valuable tool for individuals in recovery, helping them avoid relapse and ensuring they receive the support needed to maintain their progress.
The app leverages evidence-based approaches to identify behavioral patterns and trigger points that may lead to relapse. By providing real-time support and connecting users to necessary resources, the app empowers recovered teenagers to navigate their recovery journey with greater stability and confidence. This approach aims to improve long-term outcomes and reduce the devastating impact of relapse on individuals, families, and communities
