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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Henry, Salekin, Md Sirajus, Lee, Jake, Claytor, Ross, Zhang, Shinan, Chi, Michael
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909831624916992
author Wang, Henry
Salekin, Md Sirajus
Lee, Jake
Claytor, Ross
Zhang, Shinan
Chi, Michael
author_facet Wang, Henry
Salekin, Md Sirajus
Lee, Jake
Claytor, Ross
Zhang, Shinan
Chi, Michael
contents 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 enables media researchers and analysts to query relevant historical plays using natural language rather than traditional filter-and-click interfaces. The agentic workflow takes a user query as input, breaks it into elements, and translates them into the underlying database query language. Accuracy and latency are further improved through carefully designed semantic caching. The solution achieves over 95 percent accuracy and reduces the average time to find relevant videos from 10 minutes to 30 seconds, significantly increasing the NFL's operational efficiency and allowing users to focus on producing creative content and engaging storylines.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07297
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Agentic generative AI for media content discovery at the national football league
Wang, Henry
Salekin, Md Sirajus
Lee, Jake
Claytor, Ross
Zhang, Shinan
Chi, Michael
Artificial Intelligence
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 enables media researchers and analysts to query relevant historical plays using natural language rather than traditional filter-and-click interfaces. The agentic workflow takes a user query as input, breaks it into elements, and translates them into the underlying database query language. Accuracy and latency are further improved through carefully designed semantic caching. The solution achieves over 95 percent accuracy and reduces the average time to find relevant videos from 10 minutes to 30 seconds, significantly increasing the NFL's operational efficiency and allowing users to focus on producing creative content and engaging storylines.
title Agentic generative AI for media content discovery at the national football league
topic Artificial Intelligence
url https://arxiv.org/abs/2510.07297