Agentic generative AI for media content discovery at the national football league

Generative AI has unlocked new possibilities in content discovery and management. Through collaboration with the National Football League (NFL), we demonstrate how a generative-AI based workflow allows media researchers and analysts to query relevant historical plays using natural language, rather than using traditional filter and click-based interfaces. The agentic workflow takes a user query in natural language as an input, dissects the query into different elements, and then translates these elements into the underlying database query language. The accuracy and latency of retrieval are further improved through carefully designed semantic caching. The solution performs with over 95-percent accuracy and reduces the average time of finding relevant videos from 10 minutes to 30 seconds, significantly increasing the NFL's operational efficiency and allowing users to focus more on producing creative content and engaging storylines.