View Proposal

Proposer
Alessandro Suglia
Title
LLM-based Copilot for Canvas
Goal
Leverage Generative AI models to create a copilot for teachers to support several activities inside Canvas
Description
Generative AI solutions have powered many breakthroughs in several fields of AI. In this project, you will leverage Generative AI models and tools, to define a private and safe Generative AI copilot for teachers that is integrated as part of the Canvas system. One use case that we would be interested in is the automatic generation of assessment material based on the material available on Canvas (e.g., presentations, documents, etc.). More technically, we will explore agentic LLM solutions to approach this problem. We will use dedicated libraries such as Microsoft AutoGen or LlamaIndex to build an autonomous agent that can satisfy the queries of the user (i.e., teacher) and support them in generating material.
Resources
https://docs.llamaindex.ai/en/stable/use_cases/agents/ https://www.microsoft.com/en-us/research/project/autogen/
Background
Url
Difficulty Level
Challenging
Ethical Approval
None
Number Of Students
1
Supervisor
Alessandro Suglia
Keywords
deep learning, neural networks, language models, generative ai
Degrees
Master of Science in Artificial Intelligence
Back to List