Project Info

Shamefully

Devpost

This project did not submit a demo video on Devpost.

Inspiration

Nearly everyone struggles with getting their goals accomplished: we set aspirations that will propel us forward but almost inevitably fall short—we lose motivation, habits die, and our goals die with them. Some existing applications help users accomplish their goals by creating stakes for if they fail, but no existing product leverages the most powerful motivator: shame. We hope to help people help themselves and get sh*t done through shaming mechanisms.

What it does

Tell Shamefully what you want to do, when you want to do it, and who will keep you accountable. If you fail to upload evidence that you've done what you set out to do, Shamefully will call your friends, tell them you've failed, and encourage them to shame you. In addition, we've built an AI coach that helps motivate you to achieve your goals when you hit setbacks.

How we built it

We split up into 2 teams and worked on the website and mobile app. The website was build with NextJS, and AWS Amplify and a couple UI libraries. Our goal was to build something pretty, and fast. The mobile app was built using flutter and firebase. The goal here was to get a prototype out as soon as possible so that we could test it. For our AI stack, we used a combination of GPT Vision and a new Voice AI service called Bland.ai that allowed us to make phone calls and have audio conversations with LLMs.

Challenges we ran into

We had a myriad of challenges, from our initial prototype not working, to one of our teammates needing to go to urgent care. On the technical side, we mainly ran into issues with the voice API and text messaging. We found out that you need 3+ business days to get a legally registered phone number to send texts with. That led us to change our plans and modify the product (which led us to the Voice API) Halfway through the hackathon, one of our teammates found himself in need of urgent care. We had to drive around Palo Alto looking for any urgent care facility that was open and accepting patients. It took a 30 min drive to find one! We had a bunch more challenges, but it was all part of the fun.

Accomplishments we're proud of

We're all strangers on the team. We all literally met on Friday, yet somehow came together to pull off something magical. The grit and determination that I saw reminded me of why I love hacking. We also built an entire mobile app, and entire website and API in 24 hours! And the best part is that product is fun to use (we're a tad bit biased)

What we learned

We learned not to sleep at 6:00 AM

What's next

Talk to users, and see if they want it. It would be nice to keep working on this and build it into a sustainable business that genuinely helps people.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • JavaScriptIn code
  • Next.jsIn code
  • ReactIn code
  • Tailwind CSSIn code
  • TypeScriptIn code

6 of 6 appear in the indexed code.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

776 KB

Source files

68

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars