Ancestory | Devpost

Inspiration

Our team members were fortunate to have gotten the chance to foster their relationships with their grandparents, especially during the pandemic. Learning more about the rich - oft-forgotten - stories of our grandparents' lives filled us with warmth. We recognized two main categories of benefits from these stories - one for the senior members of a family and one for the younger members. Sharing meaningful stories helps senior members feel more connected to their families at an age marked by increased loneliness and a gradual loss of memories due to conditions. Similarly, sharing meaningful stories helps younger members appreciate their family's legacy even more. The experience provided by Ancestory also helps everyone look back on their life stories with nostalgic gratitude.

What it does

Ancestory is a web application where you can record a conversation that gets passed through AI to glean important information about the characters featured in the story, the place and time of the story, a summary of the story, etc. This important information is featured as a "node" on the knowledge graph of the senior member's life stories. One can explore the different stories and click on each to read more about the story that was narrated.

How we built it

We built it using React with TypeScript for the front end, NextJS, DeepGram for Speach to Text, and Together AI to run the LLMs on the transcript.

Challenges we ran into

One challenge we ran into was drawing an engineering design of how the different features and functionalities across the stack interact with each other. Another challenge involved some technical difficulties in using some technologies.

Accomplishments that we're proud of

We're also proud of learning new technologies and learning how to learn new technologies through leveraging the support of mentors and sponsor representatives.

What we learned

We learned how to brainstorm a product idea. We had to adopt a lot of product thinking in identifying pain points from our observations, market research data to support our hypothesis, and prioritizing features in the 36-hour sprint. We also learned how to design engineering projects thoroughly before we begin building.

What's next for Ancestory

We're very excited about our idea and want to continue to develop it. We want to make the knowledge graph more immersive by including the ability to filter stories based on the people featured in it and the ability to play snippets of the conversation where the individuals seemed the happiest in an attempt to capture the vibe of the story for posterity. We're planning on continuing to build this out and potentially expand its application to a VR app!