We are proud to be the

Headline sponsor

YHACK 2024

Yale's largest hackathon with participants from around the world and opportunities to win grand prizes.

October 5, 2024

Tsai Center for Innovative Thinking at Yale, New Haven, Connecticut

Schedule

Thursday, October 03

Time

Topic

Location

20:00 ET

Pre-Hackathon Workshop

Saturday, October 05

Time

Topic

Location

08:00 ET

Check In & Breakfast

Tsai Center for Innovative Thinking at Yale

10:00 ET

Opening Ceremony

Tsai Center for Innovative Thinking at Yale

11:00 ET

Hacking: START!

Tsai Center for Innovative Thinking at Yale

13:00 ET

Lunch

Tsai Center for Innovative Thinking at Yale

18:00 ET

Dinner

Tsai Center for Innovative Thinking at Yale

22:00 ET

Snacks

Tsai Center for Innovative Thinking at Yale

Sunday, October 06

Time

Topic

Location

10:00 ET

Hacking: STOP!

Tsai Center for Innovative Thinking at Yale

11:00 ET

Brunch

Tsai Center for Innovative Thinking at Yale

12:00 ET

JUDGING

Tsai Center for Innovative Thinking at Yale

15:00 ET

Closing Ceremony

Tsai Center for Innovative Thinking at Yale

Introduction

Fetch.ai’s vision is to create a marketplace of dynamic applications. We are empowering developers to build on our platform that can connect services and APIs without any domain knowledge.

Our infrastructure enables ‘search and discovery’ and ‘dynamic connectivity’. It offers an open, modular, UI agnostic, self-assembling of services.

Our technology is built on four key components:

Agents - AI Agents are independent decision-makers that connect to the network and other agents. These agents can represent data, APIs, services, ML models and people.

Agentverse - serves as a development and hosting platform for these agents.

AI Engine – enables humans to interact with the dynamic agent marketplace using natural language to execute the objective.

Fetch Network - underpins the entire system, ensuring smooth operation and integration.

Challenge statement

The world is evolving rapidly, with new technologies pushing the boundaries of what's possible. Fetch.ai challenges you to explore the power of AI Agents in solving real-world problems across various domains like the automotive and financial industries. Your task is to apply intelligent agent-based technology from Fetch.ai to one of the following areas, addressing critical issues in sustainability, education, interactive media, and healthcare.

Sustainability Challenge: Design an AI Agent that optimizes energy consumption and efficiency for smart vehicles. The agent should analyze driving patterns, vehicle health, and external factors such as traffic and weather to reduce the overall carbon footprint. It must securely share data between public and private entities, ensuring sensitive information remains confidential. Consider how this data-sharing can improve the sustainability of transportation networks by promoting energy-efficient practices and reducing environmental impact.
Education Challenge: Develop an AI Agent that personalizes educational content and feedback based on a user's learning history and preferences while adhering to standardized curricula. The agent should ensure the secure management and sharing of educational data across various platforms, protecting sensitive information. Additionally, explore how the agent can balance personalization with maintaining educational standards and how it can adapt to different learning environments to enhance educational outcomes.
Interactive Media Challenge: Create an AI Agent that curates, sorts, and presents user-generated content, such as reviews and recommendations, for specific points of interest like restaurants, tourist attractions, or service providers. The agent should be able to filter through vast amounts of data to deliver the most relevant and credible information to users. It should also adapt its recommendations based on the user's past interactions and preferences, ensuring accuracy and reliability in the information shared.
Healthcare Challenge: Innovate an AI Agent designed to assist in emergency situations, such as vehicle crashes or high-stress driving conditions. The agent should quickly assess the situation, provide real-time guidance, and securely share vital information, such as the vehicle's location and occupants' health data, with emergency responders. Your solution should prioritize maintaining user privacy and ensuring that sensitive health information is only shared with authorized parties.

Choose one of the areas above to utilize your AI Agents creatively. Consider how your AI Agent can support entrepreneurs and small businesses in managing financial data, optimizing business operations, or improving customer engagement. The agent should be able to securely handle sensitive financial information, assist in decision-making processes, and adapt to the evolving needs of a growing business. Additionally, think about how your AI Agent can contribute to the success of startups and scale-ups by providing innovative tools and insights that drive growth and efficiency.

Additional Information : If you want to learn more about uAgents through articles, please Click Here.

You can post all your queries in the #innovation-labs channel on Discord.

Submission Link: Devpost

Fetch.ai tech stack

New to Fetch.ai?

This flowchart can get you to where you want to be:

Quick start example

This file can be run on any platform supporting Python, with the necessary install permissions. This example shows two agents communicating with each other using the uAgent python library.
Read the guide for this code here ↗

from uagents import Agent, Bureau, Context, Model
    class Message(Model):
        message: str
    
    sigmar = Agent(name="sigmar", seed="sigmar recovery phrase")
    slaanesh = Agent(name="slaanesh", seed="slaanesh recovery phrase")
        
    @sigmar.on_interval(period=3.0)
    async def send_message(ctx: Context):
       await ctx.send(slaanesh.address, Message(message="hello there slaanesh"))
        
    @sigmar.on_message(model=Message)
    async def sigmar_message_handler(ctx: Context, sender: str, msg: Message):
        ctx.logger.info(f"Received message from {sender}: {msg.message}")
    
    @slaanesh.on_message(model=Message)
    async def slaanesh_message_handler(ctx: Context, sender: str, msg: Message):
        ctx.logger.info(f"Received message from {sender}: {msg.message}")
        await ctx.send(sigmar.address, Message(message="hello there sigmar"))
        
    bureau = Bureau()
    bureau.add(sigmar)
    bureau.add(slaanesh)
    if __name__ == "__main__":
        bureau.run()