Build an online game for kids that can be embedded in the Louisville Bats website and promoted in the stadium with a QR code. Help the Bats drive website traffic and modernize the traditional kids' activity book.

The game can include baseball gameplay, a design-your-own-uniform character, trivia, or another creative idea that fits the Bats' brand.

Announced reward: 10 tickets to a Bats game on September 13, 2026, plus 5 Bats swag bags. The Bats have said they are open to rewarding multiple teams; any additional awards are subject to sponsor confirmation.

Opt in to this bounty when submitting your project. Teams may pursue at most two sponsor bounties.

Original brief: https://luma.com/blast/OJtHsFL7E7

Google Swag Kits

It’s time to push the boundaries of what's possible with AI using Google Gemini. Check out the Gemini API to build AI-powered apps that make your friends say WHOA. So, what can Gemini do for your hackathon project?
Understand language like a human and build a chatbot that gives personalized advice
Analyze info like a supercomputer and create an app that summarizes complex research papers
Generate creative content like code, scripts, music, and more
Think of the possibilities… what will you build with the Google Gemini API this weekend?

Wireless Earbuds
Deploy natural, human-sounding audio with ElevenLabs. Create realistic, dynamic, and emotionally expressive voices for any project, from interactive AI companions to narrated stories and voice-enabled apps. ElevenLabs will empower you to build rich, immersive experiences without the need for actors or complex audio production, using simply the power of AI.

Integrate fully autonomous audio experiences into your hack with ElevenLabs and give your project a voice, along with giving your team the chance to win some wireless earbuds!

Portable Screens
Vultr empowers hackers to bring their high-performance projects to life instantly; providing everything from the speed of one-click deployment and scalable cloud compute, to specialized Vultr Cloud GPUs that can power AI-driven applications. We want you to push the limits of what can be built when infrastructure is no longer the bottleneck!

Sign up for a Vultr account today and claim your free cloud credits! Take your next hack to the cloud with Vultr for a chance to win some awesome portable screens for you and your team!

Tile Essentials Pack
Every AI model API is stateless by default. That means your app forgets everything the second a session ends. State management should be the first step of any AI build, regardless of what LLM you are using, and Backboard gives you that for free. But Backboard is not just state management. It is a single, unified API built on the world's #1 AI memory that gives you everything you need in one place: long-term memory, RAG, embeddings, tool calls, model routing across 17,000+ LLMs, and persistent context that stays alive across every page refresh, session, and user. No stitching together five different services. One API. One integration. Built on the best memory in AI.

Here’s just a small list of things Backboard can make possible for your AI app!

AI-powered Travel Guide: Remembers allergies and preferences from past trips.
Personalized Fitness Coach: Adjusts workouts based on progress and injury history.
Smart Home Controller: Learns routines over time to anticipate lighting and climate preferences!

Use Backboard to build a seamless, persistent user experience without the usual infrastructure headache! Each winning team member will receive a Tiles Essentials Pack because, just like AI, we all need an occasional reminder of where things are!

Raspberry Pi 4
Play with industry-leading LLMs on a single account using the Snowflake APIs. Adding AI capabilities into your application can be as simple as a single CURL command to Snowflake’s REST API.

Build customized applications, RAG powered chat bots, or embed AI-powered features into your app in half the time with half the hassle. Get started for free with a special, student 120-day Snowflake trial and check out this repository for an example of the Snowflake REST API in action.

Reward: $100 and an interview for internships.

Build models to predict winning sports outcomes. Data will be provided to teams for two sports: UFC and basketball.

UFC: Build a round-win prediction model and a win-method prediction model based on historical fight data. Both models should achieve greater than 50% accuracy.

Basketball: Data will be provided for NBA, WNBA, men's college basketball, and women's college basketball. Build a model that predicts wins over 50% for each league.

Present the findings in an engaging, easy-to-digest way for a casual audience, with a breakdown of how you calculated the models so they are verifiable and repeatable.

Bonus: Additional models that aid in calculating point spreads or other prop bets.

STAATY is a small team building a fan engagement tool to transform how people consume sports. The team is excited to meet participants and answer questions.

From the sponsor: Danny Morton, STAATY.com.

Opt in when submitting your project. Teams may pursue at most two sponsor bounties.

Reward: $250 + a real product integration (pending approval).

Build an agentic interviewer that takes an assignment and comes back with the story for marketing content, such as social posts and blogs. The user briefs it like an editor briefs a reporter: who is being interviewed, the topic, and the content needed, such as a founder story, customer case study, or podcast segment.

From the brief, the agent works out its own line of questioning, conducts a live, roughly 10-minute voice or text interview, and turns it into the assigned content plus the pull quotes worth keeping.

The hard part is hosting the interview. A great interviewer is warm and human: it follows up with curiosity, abandons its plan when something better becomes apparent, and still lands the assignment.

It should run as an MCP tool inside Claude, which is what the winning team will keep building on with Prologue.

Judged on the interview, not the tech: Would the interviewee do it again on purpose? Does the output read like a story or like meeting minutes? Does the interview introduce a new valuable asset for a knowledgebase?

Participants can have access to Prologue's head of product, Chris Gleim, for questions before starting. This is a real product on the roadmap for Prologue's software, Premise. Participants will receive user access to Premise's current state, which is in the middle of a pivot.

From the sponsor: Brad Luttrell, Prologue Stories LLC.

Opt in when submitting your project. Teams may pursue at most two sponsor bounties.

Organization
Swell
The challenge
Swell Bounty: Dupe Something

Pick a product you use every day. Instagram, Google Calendar, Slack, Linear, Superhuman, whatever. Rebuild the core of it well enough that someone could use it as an MVP and believe in the future of the product. It must work, it must be user friendly, it must make at least 1 critical improvement on the original.
Anything else
Bonus point: make it smarter with Swell in any way that improves the product.

What's Swell: Swell maps how people's personalities are wired (and evolvable) across 63 traits, predicts repeating behavior dynamics and patterns based on those traits, & uses that to help people change the patterns that they want to stop repeating. Connect a (mock) Swell account and use it. A calendar that knows why your 2pm with Dana always runs long. A group chat app that gives you compatibility across your group. Mock data and shapes provided.

Finding a doctor shouldn’t feel like searching a spreadsheet. Build a fast, friendly tool that helps people find nearby doctors and healthcare facilities, understand their options, and save the providers who matter to them.

WHAT TO BUILD
Let users search for physicians and facilities by name and ZIP code inside Kynd Choice.
Show useful provider details, including specialty, credentials, location, and NPI.
Check whether a selected provider participates in each displayed plan’s network.
Clearly distinguish confirmed in-network, out-of-network, and unknown results.
Add a Recommend a Doc feature when a user selects a plan that does not cover their provider.
Recommend comparable in-network providers based on specialty, proximity, and other available attributes.
Explain why each provider was recommended.
Prize / reward
$200 cash + swag
Anything else
STRETCH GOAL
Support provider preferences for an entire household and rank plans by how well their networks cover everyone’s preferred care.
GOOD TO KNOW
This must be built into the Kynd Choice shopping experience, not a HealthSherpa-hosted shopping flow.
HealthSherpa ONE can provide provider identity and NPI data. Plan-network participation must come from verified Kyndly network data or another authoritative source—it should never be inferred or presented as confirmed when unknown.