{"slug":"bundesliga-builds-captain-an-agentic-ai-companion-for-fans-on-amazon-bedrock","url":"https://findausecase.com/use-cases/bundesliga-builds-captain-an-agentic-ai-companion-for-fans-on-amazon-bedrock","title":"Bundesliga builds Captain, an agentic AI companion for fans, on Amazon Bedrock","description":"Bundesliga Media built Captain, an AI companion embedded in the official Bundesliga app that answers fan questions via text-to-SQL over match data and runs research agents that surface personalised insights as events happen. A model-routing layer sends about 45% of questions to Amazon Nova Pro and the rest to Claude Sonnet 4; the AWS blog reports a 35% reduction in chat assistant service costs with the same answer accuracy.","company":"Bundesliga","industry":"Media & Entertainment","aiCapabilities":["Agentic AI","Conversational AI","Generative AI"],"technology":["Amazon Bedrock","Amazon Nova Pro","Claude Sonnet 4","Amazon Athena","Amazon S3 Tables"],"deployment":"Unknown","problemStatement":"Bundesliga wanted to give fans a single conversational interface for live stats, historical trivia, tactical analysis and video highlights, and to surface insights that fans would never find on their own or didn't know to ask for.","solutionApproach":"Bundesliga Media built Captain, an agentic AI companion embedded in the official Bundesliga app. A chat service uses a text-to-SQL workflow in which an LLM converts a fan's question into a database query that Amazon Athena runs against statistical data stored in Amazon S3 Tables, and a second LLM call turns the results into a natural-language answer. A model routing layer classifies each question and sends straightforward ones to Amazon Nova Pro and medium and complex ones to Claude Sonnet 4 in Amazon Bedrock. A research service built on the Strands Agents SDK with Amazon Bedrock triggers agents on events such as goals to surface personalized insights, and Amazon Bedrock Guardrails screen inputs and check that outputs are grounded.","businessValue":"Roughly 45% of fan questions qualify for the more economical Nova Pro path, and this dynamic approach delivered a 35% reduction in chat assistant service costs while maintaining the same answer accuracy.","evidence":{"band":"high"},"sourceUrl":"https://aws.amazon.com/blogs/media/how-bundesliga-built-captain-an-ai-agent-for-fans-using-amazon-bedrock/","dates":{"publishedAt":"2026-10-13T05:50:44.975Z","publishedAtSource":"pipeline","updatedAt":"2026-10-13T05:50:44.975Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/bundesliga-builds-captain-an-agentic-ai-companion-for-fans-on-amazon-bedrock. Bulk republication requires permission."}