SunnyHacks is a student-led hackathon focused on AI agents: systems that can reason, make decisions, and take actions on their own. The event brings together students from a range of technical and academic backgrounds to explore how these systems can be designed, applied, and used in real-world setting.

Recent advances in large language models and tool-integrated AI have shifted attention from static models to more dynamic systems capable of multi-step problem solving. SunnyHacks is designed to give students direct exposure to this shift, encouraging them to go beyond simply using AI and instead build systems that can tasks with minimal human input.

Heavy use of AI in the creation of the actual agent is discouraged :(

Requirements

What to Build

Build a specialized AI agent in a domain of your choice that can take actions to accomplish a task.

Your agent should:

  • Execute a multi-step task end-to-end
  • Make decisions autonomously (not just respond to prompts)

What to Submit

A video showcasing your agent at work with a voiceover or subtitle description.

Hackathon Sponsors

Prizes

1 non-cash prize
1st Place
$0 in cash
1 winner

CodeCrafters 2 Year VIP Membership ($720)

2nd Place
$0 in cash
1 winner

CodeCrafters 1 Year VIP Membership ($360)

3rd Place
$0 in cash
1 winner

CodeCrafters 6 Month VIP Membership ($240)

Most Popular
1 winner

To be determined

Devpost Achievements

Submitting to this hackathon could earn you:

Judges

Vaibhav Patel

Vaibhav Patel
AI Engineer, Abu Dhabi Investment Authority

Ankur Bhatnagar

Ankur Bhatnagar
Sr IEEE Member

Ratna Kumar Bonagiri

Ratna Kumar Bonagiri
Senior Distributed Systems and Data Platform Architect, IEEE Senior Member

Swarnamalya Mohan

Swarnamalya Mohan
Senior AI/ML Advisor, FedEx

Judging Criteria

  • UI/UX
    is your agent visually appealing and easy to use
  • Innovation & Creativity
    How original is the idea? Does the agent introduce a novel workflow, capability, or application instead of simply wrapping an existing chatbot?
  • Technical Execution
    Quality of engineering, architecture, reliability, and implementation. Effective use of memory, tool selection, decision-making, and error recovery.
  • Autonomy
    The degree to which the AI independently plans, reasons, adapts, and completes tasks.

Questions? Email the hackathon manager

Tell your friends

Hackathon sponsors

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.