A multi-agent AI system that automatically ret rieves the latest football news and compiles it into a newsletter.
Project Overview
Project Overview
Can you provide a brief overview of the project you've been working on?
The AI Football Newsletter Crew project utilizes multiple AI agents, each assigned specific roles, to collaboratively gather and compile the latest football news into a cohesive newsletter. This system is powered by crewAI, enabling effective collaboration among agents to accomplish complex tasks.
Purpose of the project
Purpose of the project
What inspired or motivated you to choose this particular project?
The project aims to streamline news aggregation and newsletter creation by automating the retrieval and compilation of football-related news. This automation reduces manual effort and ensures timely delivery of up-to-date information to readers. My motivation was to automate a task that previously required significant resources and manpower.
Technical Details
Technical Details
Could you explain the technical aspects of your project? What software, tools do you use?
The system is developed in Python and employs Poetry for dependency management. It leverages the crewAI framework to manage the interactions between multiple AI agents. The agents' tasks and configurations are defined in YAML files (config/tasks.yaml and config/agents.yaml), enabling flexibility and scalability.
The system involved 4 different agents, each of these were given a specific task. The first one is the Editor Agent, which acts the manager for the whole task. Then there are three subordinates: News Fetcher Agent, News Analyzer Agent, and the Newsletter Compiler Agent.
To operate, the system requires API keys for OpenAI and Serper, which should be specified in a .env file.
Challenges and Solutions
Challenges and Solutions
Were there any significant challenges you encountered during the project, and how did you overcome them? Can you share a specific problem-solving moment that stands out in your project?
The main challenges involved prompt engineering and architectural design. Initially, the system did not correctly integrate all agents into the newsletter production process. To resolve this, I had to re-engineer the architecture to ensure all agents were effectively contributing to the task.
Collaboration and Teamwork
Collaboration and Teamwork
Did you collaborate with other students or team members on this project?How did teamwork contribute to the success or progress of your project?
I developed this project individually as part of my Statistical Learning Course.
Learning and Takeaways
Learning and Takeaways
What key lessons or skills have you gained from working on this project?
I learned how to automate large-scale tasks using multi-agent AI systems.
Future Development
Future Development
Do you have plans for further development or improvement of your project in the future?
I may deploy the application live and allow users to customize the newsletter topic. So far, it has been well received by the open-source community, with approximately 20 stars on GitHub.
Check other student projects
Check other student projects