DogeRace

Hackathon TA Diagram

Credentials

username1 password1

Inspiration

We were inspired by the rapid rise of AI models—and the real challenge users face choosing the right one for their specific needs. Reviews often say “they’re all good,” but don’t help with targeted use cases like stable art generation or accurate stock predictions. We wanted to make comparing AI models transparent, fun, and engaging.

What it does

DogeRace is a Bolt-based game where users bet on which AI model will perform best in real-world prediction challenges. Each race is a head-to-head AI comparison, with results stored immutably on the Algorand blockchain for verifiable, trusted proof. Users earn crypto payouts for backing the winning AI.

How we built it

We designed DogeRace with AWS serverless at its core. API Gateway routes requests to AWS Lambda, which runs AI model predictions and our Assessor AI to evaluate results. DynamoDB stores user data and race history with low-latency scalability. Our architecture ensures easy maintenance, automatic scaling, and cost efficiency. Algorand is integrated to record race outcomes immutably for full transparency.

Challenges we ran into

We faced challenges orchestrating multiple AI model calls within Lambda’s time limits, integrating testnet crypto wallet flows, and ensuring seamless communication between the Bolt front-end and our AWS serverless APIs.

Accomplishments that we're proud of

We’re proud of building a truly serverless app that can scale seamlessly without managing infrastructure. Our architecture delivers an automated, secure, and reliable backend to support real-time AI competitions with blockchain-verified results.

What we learned

We learned how powerful AWS serverless services are for orchestrating complex workflows. Combining Lambda, API Gateway, and DynamoDB allowed us to move fast while maintaining strong architecture best practices.

What's next for DogeRace

We plan to add more AI models, richer user profiles, advanced betting mechanics, NFT-based rewards, and deployment on Algorand mainnet for real payouts. We’re also exploring the AWS Marketplace to distribute and scale our solution to more users and organizations globally.