Project Info
Inspiration
Our inspiration for Synthify stemmed from our experiences as students and researchers at the University of Pennsylvania. We noticed significant limitations in traditional survey platforms, particularly in terms of representation, sample size, and cost. This inspired us to develop a solution that could address these challenges and revolutionize the process of data collection for human-centric research.
What it does
Synthify is a platform that generates artificially intelligent personas to synthetically complete surveys for human data-centric research. Researchers can create accounts, design surveys, and recruit personas based on demographics such as age, race, and location. The platform utilizes custom large language models to automatically complete surveys, providing researchers with structured data outputs.
How we built it
We built Synthify by integrating custom large language models into the platform and developing features for user authentication, survey design, and persona recruitment. We utilized technologies such as Python, JavaScript, and various machine learning libraries to create a seamless user experience and ensure the accuracy of synthetic data generation.
Challenges we ran into
One of the main challenges we encountered was developing a reliable method for generating synthetic data that closely mimics real data. Additionally, integrating large language models and ensuring their efficient functioning within the platform presented technical hurdles that we had to overcome.
Accomplishments we're proud of
We are proud to have successfully built all core features of Synthify and to be piloting studies with researchers at prestigious institutions such as the Wharton School and the Annenberg School of Communication. Furthermore, securing funding and support from organizations like Microsoft for Startups and the Wharton School has been a significant accomplishment for us.
What we learned
Through our journey with Synthify, we have learned the importance of addressing key issues in survey design and the potential of synthetic data in human-centric research. Additionally, we have gained valuable insights into user needs and preferences, driving our continuous improvement efforts.
What's next
Moving forward, we plan to enhance Synthify with additional features such as synthetic interviews and social media interactions. Furthermore, we aim to expand our partnerships with academic institutions and research organizations to broaden the application of synthetic data across various industries. Ultimately, we envision Synthify as a pioneering solution in data creation for research and innovation.
This project did not link a GitHub repository.
Analysis
No indexed repository for this project, so there are no commit stats to show.
Technology
- LangChainUnchecked
- Mistral AIUnchecked
- PythonUnchecked
- VercelUnchecked
No repository was indexed for this project, so these Devpost claims have not been checked against code.
AI coding agents
No repository was indexed, so agent usage could not be checked.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
No repository was indexed, so there is no codebase to measure.
This project did not link a GitHub repository, so there is nothing to diagram.
This project did not link a GitHub repository, so its feature claims have not been checked against code.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.