NFL franchises adopt artificial intelligence to modernize player evaluation and draft strategy

NFL franchises are increasingly using artificial intelligence to update how they evaluate prospects and plan for the annual player draft. Teams are adding AI-driven tools alongside traditional scouting during the current draft cycle, aiming to make decisions more consistent by leaning on objective, data-based assessments of performance and projected fit.

A central goal is to address long-standing challenges in measuring athletic traits, especially when standardized testing is missing. AI systems can review college game film and generate speed ratings for players who do not complete common benchmarks such as the 40-yard dash. Officials involved in these efforts describe the approach as a way to translate what appears on tape into comparable metrics that can be used across positions and prospect pools.

The film-based outputs are described as similar in concept to the league’s Next Gen Stats, in that they produce data points intended to clarify how physical attributes may translate to specific NFL roles. In one example cited from the current cycle, AI analysis of Ohio State safety Caleb Downs indicated a lower game speed relative to other top safeties.

That result was presented as a signal that his profile could align more naturally with a “box-slot” safety role rather than a deep coverage assignment.

Beyond individual measurements, teams are also using AI to navigate large stores of existing information. Microsoft, identified as a league partner, provides an internal platform that contains historical combine data. Teams can access that database using natural-language queries, allowing staff to pull and compare information without relying solely on manual searches or specialized query building.

Teams using these tools describe the benefit as moving from simply collecting data to extracting usable guidance for planning. That can include how a player might be deployed, what traits are most relevant to a role, and how a prospect’s profile compares with historical combine outcomes stored in the system. The intent is to support draft-day choices and inform development plans after a player enters the league.

At the same time, the technology is not positioned as a replacement for human judgment. The approach described in the draft cycle keeps evaluators in the loop, with AI serving as an additional layer of analysis rather than an automated decision-maker. How heavily teams weigh these outputs versus traditional scouting remains a key unknown, and the league-wide impact will depend on how consistently clubs integrate the tools into their processes.