NFL Combine gains real-time insights for informed draft day decisions with Azure AI

Each year, the NFL Combine brings together coaches and scouts from its 32 clubs to evaluate the talent and performance data of more than 300 of the best athletes in the world. The decisions made at the Combine shape the future of football clubs and players alike. Delays or oversights during the event can come with a cost. 

The need to speed access to data and insights within the existing NFL Combine App drove the latest evolution of the app, which has supported clubs at Combine for several seasons. The addition of an AI assistant, designed to allow scouts and coaches to get instantaneous player insights and ask their questions with common Combine vernacular, marked a major leap forward.  

“We went for it! We decided to dramatically change the game for these clubs by giving them exactly what they need when they need it,” explains Jeff Foster, President of National Football Scouting (NFS). “We wanted to transform hours of tedious, manual effort into seconds of grab-and-go data.”  

Delivering real-time answers with Azure AI

To integrate the new app assistant ahead of the 2025 Combine, the NFL worked with longtime Microsoft development collaborator SOUTHWORKS to integrate a conversational AI assistant into the existing Combine platform. The architecture brought together Azure OpenAI for natural language processing; Azure Cosmos DB for fast, structured data access; and Azure Container Apps for scalable, event-day performance without infrastructure management. As a result, the assistant could interpret sideline queries, analyze and compare player data, and respond in real time, providing scouts with accurate player data and fast performance. 

At the core of the assistant is Azure OpenAI Service, which runs the latest GPT-series model. To power the assistant’s experience, developers built on a tightly integrated stack of Azure services that handle natural language interaction, data processing, and scale.   

“Now I just ask a question as I would ask you a question—and get what I need in seconds. It used to take hours, sometimes not even possible until after the Combine,” says Jacqueline Davidson, VP of Football Research for the Tampa Bay Buccaneers.” For Davidson, that shift turned a time-consuming process into a real-time edge. The solution didn’t just speed things up; it brought insight exactly when she needed it. 

Supporting the assistant’s intelligence is Container Apps, hosting both the assistant’s API and the background services responsible for fetching and normalizing data from the NFS’s systems. Choosing Container Apps gave the team a fully managed compute layer that not only scaled on demand for event-day traffic, but supported enterprise-grade reliability, security, and compliance—all without the overhead of managing infrastructure. 

At the data layer, Azure Cosmos DB serves as the data store behind the assistant, caching structured player information so the assistant can respond quickly. In future iterations, Azure Cosmos DB will also facilitate multi-turn interactions by acting as the assistant’s memory layer, but in this release, all responses are single-turn and stateless. Together, this architecture gave the Combine’s new AI assistant a production-grade foundation—highly secure, scalable, and responsive—ready for real-time sideline use within the app that teams already trusted. 

 For club personnel, the benefit was clear: natural language queries turned manual reports and comparisons into instant answers during critical Combine moments. 

Building a real-time solution that’s fast and scalable

For the development team, building and integrating the new AI assistant on a tight timeline—within an already operational Combine App—meant leaning on a clear development philosophy: move fast, reduce complexity, and build for real-world usage.  

A major part of that success came from choosing Container Apps as the assistant’s compute layer. “This gave us a clean, cloud-native foundation,” says Pablo Damiani, Head of Practice at SOUTHWORKS. “Because we didn’t have to manage infrastructure, we could focus entirely on assistant logic and system behavior, not deployment pipelines or scale policies.”  

Azure Cosmos DB was just as critical for enabling performance. It acted as a fast, resilient cache, storing normalized player data so the assistant could respond instantly without repeatedly querying upstream APIs. For the team, Azure Cosmos DB brought the speed and flexibility they needed under real-world load. “We chose Azure Cosmos DB for its exceptional performance and ease of use,” explains Damiani. “Being schema-less meant we could store JSON documents containing NFL Combine results without upfront schema planning, which was a huge advantage given our tight schedule.”

Beyond architecture choices, SOUTHWORKS leaned into engineering best practices: 

• Automated testing and prompt QA ensured the assistant could sustain responsiveness during peak sideline usage.

• Early instrumentation with Application Insights in Azure Monitor helped the team track latency, token consumption, and behavioral patterns, surfacing performance insights in real time. 

• Usage data during the Combine helped fine-tune the experience according to how scouts and coaches actually interact with the assistant, not just what was expected. 

“With these kinds of experiences, you can’t always predict how people will use it,” says Damiani. “But if you build in observability from the start, you can learn fast—and keep making it better.” That approach carried through from prototype to production, pairing agile engineering with a deep focus on the user experience.

Damiani credits the playground in Azure AI Foundry as perfect for rapid prototyping. He adds, “It’s like talking with someone who knows everything about every player and can respond with drill results on the fly. That’s the value the AI experience brings to the app.”  

Proven at the Combine, built for what’s next

Although the Combine App has been a trusted tool for years, the event introduction of the new AI assistant—built and integrated in just weeks—marked a turning point for in-the-moment evaluation. This wasn’t a tech demo. It was a live, production-scale enhancement, tested under the pressure of one of football’s most high-stakes events and proven in real time.

“The Combine is a very special event for these exceptional athletes. A player’s draft future relies on accurate data and fast insights,” explains Foster. “Working together with Microsoft, we look forward to delivering even more ‘wow’ app breakthroughs next year by expanding its capabilities to include historical player data comparisons and richer prompt capabilities, improving the Combine experience for everyone.”      

Rapidly built and tested under live Combine conditions, the assistant proved its value where it mattered most—on the competitive field. 

Discover more about the NFL Combine here.