About Generative AI and Cloud Computing
Generative AI refers to a type of artificial intelligence designed to generate new content, data, or outputs that are not explicitly programmed in advance. It involves models that can create new examples or samples within a given domain, such as images, text, music, or other types of data.
Cloud Computing is the practice of using a network of remote servers hosted on the internet to store, manage, and process data, rather than a local server or a personal computer. It allows you to focus on developing, rather than having to worry about providing all the hardware. One of the biggest cloud service providers out there is Amazon Web Services (AWS).
Theme
Our challenge invites you to explore generative AI and develop AI‑powered tools that support communities by reducing friction, improving coordination and connection, and making opportunities and information more accessible. This theme invites teams to identify a real problem that students observe in a specific community they belong to or are connected to (e.g., volunteer, neighbourhood, club, etc.), one that their given community is personally impacted by and motivated to address. Teams should clearly define the community, the problem being experienced, and who is affected.
Criteria
Prior to and throughout the hackathon, please keep the following judging criteria in mind as you develop your project. These criteria should guide your approach from initial ideation through to final implementation and presentation.
Your project is expected to demonstrate the following:
- Creativity and Originality: The innovativeness and uniqueness of the generated solution.
- Potential Use Cases: The clear identification of potential use cases, end users, and overall impact in the given community that you have identified.
- Technical Implementation: The complexity and performance of the AI model and the effectiveness of the cloud services deployed for the solution.
- User Interaction: The intuitiveness and usability of the user interface in influencing the generated solution.
- Presentation: The clarity, coherence, and persuasiveness of the final presentation.
Pre-Hackathon Jam Session
Ahead of the hackathon, we’re hosting an AWS Jam session as a hands-on preparation experience. AWS Jam is an interactive, gamified learning event created by Amazon Web Services where participants work to solve real-world cloud challenges across a variety of AWS services. We highly recommend that you participate in the Jam session. There is no cost to participate.
Virtually on Monday, May 4th, 2026, 11:00AM - 11:30AM the AWS Jam Session on AWS concepts and tools will be posted in the Discord channel.
For frequently asked questions: AWS Jam FAQ
- 9:00AM: Check in and refreshments
- 9:15AM: Introductions and icebreakers
- 9:30AM: Hacking commences
- 12:00PM: Lunch (provided)
- 4:00PM: Hacking ends
- 4:10PM: Presentations start
- 5:30PM: End of Hackathon!
- UBC student card
- Adapters
- Laptop and charging cables
- A water bottle
- Reusable coffee mug, containers, and cutlery
West Mall Swing Space Building: 2175 West Mall, Vancouver, BC V6T 1Z4. The registration booth will be set up near the building entrance beside the elevator
- No plagiarism
- Code must be on GitHub and open sourced
- Any private datasets used must not contain personally identifiable information
- Project design and development must start at the hackathon’s beginning, but preprocessed and structured data is allowed
- All team members must be physically present in the event
- Team presentation: Total 5 minutes (3 min presentation, 2 min Q&A)
- We recommend talking about the potential real world impact of this project
- DEADLINE: There is a hard deadline and requirement to submit the following in your Discord team channel by 4:00PM:
- The link to your public GitHub repository
- To judge the technical details of your solution, you must include an architecture diagram (try out draw.io, or any other tool)
- A list of AWS services used for your project
- Two to five sentences describing your project and the identification of potential use cases, end users, and overall impact in the given community that you have identified
- Late submissions will lead to disqualification
For frequently asked questions and tips, please visit FAQs
- Introduction to Generative AI - Art of the Possible
- Planning a Generative AI Project
- Introduction to LangChain - LangChain is a framework for developing applications powered by language models
- Prompt Engineering Best Practices - Prompt engineering best practices for LLMs on Amazon Bedrock.
-
- General Prompt Engineering using Party Rock - Learn General Prompt Engineering using Party Rock (free to use).
- Anthropic Claude on Party Rock - Learn Anthropic Claude Interactive Prompt Engineering tutorial on Party Rock (free to use).
- Anthropic’s Official Documentation - Anthropic’s Official Prompting Documentation
- AWS Bedrock Samples Repository - AWS's Official GitHub Samples Repository
- AWS GenAI Quick Starts - AWS's Quick Starts for GenAI Repository
- AWS Bedrock PDF Chat - Example of PDF Chat using Amazon Bedrock
Retrieval-augmented generation (RAG) for large language models (LLMs) aims to improve prediction quality by using an external datastore at inference time to build a richer prompt that includes some combination of context, history, and recent/relevant knowledge
-
More in-depth intro Retrieval Augmented Generation (RAG) for LLMs
- Building AI-powered search in PostgreSQL using Amazon SageMaker and pgvector (Blog post)
- AWS Samples (GitHub) - RAG with Amazon Bedrock and PGVector on Amazon RDS
- Knowledge Bases now delivers fully managed RAG experience in Amazon Bedrock
- Knowledge Base for Amazon Bedrock - Documentation
- Amazon OpenSearch Service’s vector database capabilities explained
- Build scalable and serverless RAG workflows with a vector engine for Amazon OpenSearch Serverless and Amazon Bedrock Claude models (Blog post)
Enable generative AI applications to execute multistep tasks across company systems and data sources
- User Guide
- Demo Video - Agents for Amazon Bedrock
- Amazon Bedrock Agents Quickstart - Functional code example
- Build a foundation model (FM) powered customer service bot with agents for Amazon Bedrock
- AWS Cloud Essentials
- Architecting on AWS - Online Course Supplement
- AWS Serverless Land - AWS Serverless examples, patterns, documentation and guidance.
Below are a few examples to help you understand the kinds of technologies and problem-solving approaches you can explore. Some are real-world projects, while others are conceptual ideas meant to inspire your creativity.
- GitHub Link: RAG-Bedrock-Titan
- Video: Implementing RAG with Amazon Bedrock and Amazon Titan - Part 1
From the creator: "In this tutorial, we will build a chatbot based on the Retrieval Augmented Context generation technique. Amazon OpenSearch Serverless is used as the vector database, Amazon Titan is used for generating text embeddings and as an LLM, and Amazon Bedrock API is used for invoking the Titan model."
A UBC CIC project that enables instructors to generate quizzes, flashcards, and other practice materials from open textbooks, while allowing students to engage with course content through a conversational chat interface. The system uses generative AI to retrieve and synthesize information from open educational resources, providing accurate, context-aware learning support. Check out the project GitHub repository.
A chatbot that helps renters navigate tenancy issues such as rent increases, eviction notices, and maintenance disputes. Built with Amazon Bedrock and a RAG-based knowledge base, it generates responses using verified provincial housing regulations and advocacy resources. A simple web interface allows users to ask questions or upload documents and receive clear, situation-specific guidance.