Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
SportAI
This talk details an Agentic AI pipeline using CrewAI to analyze NFL, NBA, and MLB data for predictive sports outcomes, showing LLMs reasoning over stats and odds.
I will be presenting my project, which uses an Agentic AI system to generate predictive insights for NFL, NBA, and MLB sports outcomes.
The core of the project is an end-to-end Agentic AI pipeline built using the CrewAI framework, specifically designed to assist bettors by providing intelligent, data-driven predictions.
Our Agentic AI system analyzes a wide range of game-related metrics, including:
Player performance history
Past game results for both teams
Betting odds aggregated from multiple sportsbooks
Latest team and player news
These inputs are processed by a set of specialized agents, each responsible for a specific domain of analysis. Their findings are then passed to higher-level performance and analytical agents, which synthesize the information.
Finally, a Decision Agent consolidates all the analyses and produces a comprehensive final prediction report, combining statistical insights, performance trends, and qualitative assessments.
All sports data—across teams, players, odds, and news—is sourced directly from SportsData.io, ensuring accuracy and real-time reliability.