What to Build

Build a LLM-powered digital assistant with a chat interface using Amazon Bedrock’s native capabilities. Use this new technology to build teams and answer various questions about VALORANT esports players, leveraging provided data sources and demonstrating effective information retrieval and analysis.

• Please read through the Submission Specifics page for full details.

What to Submit

• Code: Provide a URL to your code repository to show how your project was built.

• Please provide access by sharing it with: [email protected], [email protected], and [email protected]
  

• Reminder: project must include a chat interface, which judges can use to interact with your submissions.

• Demo: Include a video (should be about 3 minutes) that demonstrates your submission. Videos must be uploaded to YouTube, Vimeo, or Facebook Video and made public.

• Judges will not be reviewing beyond 3 minutes.
  

• Methodology Write Up: Should include a short explanation of how the model was trained and any notes about the methodology underlying team composition outputs. Include information about any other data sources used, and your findings and learnings as you worked through the project.
  

• Tooling: Include an explanation of the AWS services used to build the project.
  

• Optional Tagging: AWS enables you to assign custom tags to your resources. A tag is a key-value pair applied to a resource to hold metadata about that resource. Each tag is a label consisting of a key and an optional value. Not all services and resource types currently support tags (see Services that support the Resource Groups Tagging API). We recommend that any infrastructure you launch be tagged with “key: vct-hackathon value: 2024”.
  

• Optional Access: Provide a public URL to your working app
  

Please check the Official Rules for full details.