The Bundesliga has long talked about turning “data into devotion,” and now it has an agentic AI companion in its official app that lets fans chat in natural language, access live stats and historical context, and view personalized video highlights—all without leaving the app.

Bundesliga is the premier professional soccer league in Germany. It built its new AI companion, called Captain, on AWS and embedded it in the official league app. For IT pros, this is more than just a clever sports-tech use case. It’s an early glimpse of what the customer experience will feel like when generative and agentic AI are not bolted on but, instead, become the primary way users navigate data, content, and services.

Understanding Captain

Captain serves as a conversational interface in the Bundesliga app, acting like a knowledgeable friend who watches every game with you. Fans can ask questions like, “How has Jamal Musiala been playing for Bayern this season compared to his national team?” and receive responses grounded in official league data, complete with stats, historical context, and relevant clips.

Key capabilities include:

• On-demand access to live statistics, historical match data, tactical analysis, trivia, and video highlights via chat.
• Proactive insights during key moments, such as goals, penalties, milestones, where AI agents surface streaks, records, or parallels to historic games.
• A “coach mode” that gamifies learning the sport, adapting explanations and daily lessons to each fan’s knowledge level.

Under the hood, Captain uses a multi-agent architecture built on Amazon Bedrock and Amazon Nova, dynamically routing each request to the appropriate model and workflow. Simple questions go to a lightweight model, while complex reasoning and data mashups are handled by more capable models, with text-to-SQL pipelines translating natural language into queries against the Bundesliga’s analytics stack. The result is a conversational front end built on a robust data platform.

The data foundation

What makes this notable is not only the UI but also the data infrastructure needed to deliver these capabilities. Historically, the Bundesliga tracked one point per player per second, generating roughly 3.6 million data points per match. With their move to 3D skeletal tracking—21 points per player at 50 frames per second—they now process roughly 200 million data points per match.

That data lands in a modern analytics and AI stack on AWS, including:

• Streaming ingestion via Amazon MSK and other services to handle real-time feeds.
• A data lake and lakehouse foundation using S3 Tables and Apache Iceberg for open, schema-evolving storage.
• Query and analytics via Amazon Athena and associated text-to-SQL workflows for on-the-fly question answering.
• Vector stores to cache question-to-SQL patterns and reduce cost on repeated queries.

On top of this, a set of agentic workflows continuously monitors live events, generates candidate “stories,” and pushes the best ones into Captain so fans see relevant narratives without having to know what to ask. This same foundation is already being used by the league to generate thousands of AI-powered narratives per season for broadcasters and editors, demonstrating how editorial and fan experiences can share a common AI backbone.

For IT leaders, a key lesson learned is that data strategy is as important as model selection in building compelling generative AI experiences.

What this signals about the future of customer experience

Captain illustrates several important shifts that will define AI-driven CX across industries.

• Apps shift to companions. Instead of forcing users to navigate menus and features, the Bundesliga consolidates multiple use cases – scores, stats, historical research, video discovery, and learning – into a single conversational surface. This mirrors what enterprises will do with “digital relationship managers” in banking, “patient companions” in healthcare, and “shopping concierges” in retail.
• From reactive support to proactive storytelling. Most chatbots answer questions; Captain also looks ahead. When a major event occurs, agents work autonomously to find interesting angles, such as a record broken, a rare streak, a historical déjà vu, and push them to fans in real time. Imagine similar patterns in other domains: an insurance AI flagging a better coverage option at renewal, or a B2B vendor surfacing adoption risks before a renewal conversation.
• Experiences become adaptive. Coach Mode exemplifies progressive disclosure: it teaches a new fan the rules while offering tactical deep dives for advanced fans, all within the same interface. That’s exactly the model enterprises will need—systems that can explain a process to a novice and to a domain expert in different ways, without duplicating apps or content.
• Static journeys are evolving into AI-driven micro-journeys. The Bundesliga is using agentic AI to stitch together micro-journeys in real time. A question triggers an answer; a research agent follows up with deeper content; a video agent suggests highlights—all personalized and sequenced. In enterprise CX, journeys will increasingly be orchestrated by AI that adapts steps, channels, and content to context, rather than by rigid workflows.

Implications for IT pros and CX leaders

For IT pros, CX improvement requires rethinking the architecture, governance, and operating models to support AI-native experiences. Here are some things to consider.

1. Start with a data-first mindset. Captain only works because the Bundesliga invested years in building a robust data foundation. That includes high-fidelity tracking, consistent schemas, and streaming infrastructure. Before promising AI companions to your business stakeholders, you need to:

• Inventory your customer data sources and identify gaps in coverage, latency, and quality.
• Rationalize schemas and metadata so AI agents can reason across systems (CRM, transactional systems, content libraries) without brittle transformations.
• Plan for real-time or near-real-time data where “moment of truth” interactions matter.

Without this groundwork, generative AI projects risk turning into expensive prototypes that can’t scale.

2. Think in terms of AI agents, not just models. Bundesliga’s architecture separates concerns into agents: a router agent to determine intent, stats agents to query the right backends, and research agents to autonomously investigate events and propose stories. IT teams should similarly design:

• Routing layers that determine whether a request is informational, transactional, or analytical.
• Specialized agents for data retrieval, verification, personalization, and safety.
• Clear SLAs and guardrails for agent interactions with core systems.

This moves you from one big LLM to an orchestrated system in which different components can evolve independently.

3. Leverage dynamic routing for cost and performance. Bundesliga explicitly uses dynamic model routing. This approach uses lighter models for simple questions and more powerful ones for complex reasoning, cutting chat costs by more than a third without sacrificing accuracy. Enterprise IT can borrow this pattern:

• Use smaller models or even retrieval plus templating for repeatable queries.
• Reserve premium models for complex, high-value interactions.
• Continuously collect analytics on query types to refine routing policies.

The result is an AI experience that scales economically rather than collapsing under inference costs.

4. Redefine UX around conversation and context. Captain’s UX is not just chat; it’s chat tightly coupled with video playback, stats visualization, and contextual recommendations. For IT and product teams, this means:

• Designing conversational experiences that can invoke micro-apps or widgets (e.g., forms, dashboards, media players) in context.
• Maintaining conversation state across channels, so a user can move from mobile to web or from chat to voice without losing context.
• Instrumenting these flows to understand where AI helps, confuses, or frustrates users.

Generative AI should be treated as a new interaction layer, not a standalone feature.

5. Treat safety and trust as first-class requirements. Captain is built on official league data and protected by content safety guardrails to prevent hallucinations or inappropriate content. In enterprise settings, this translates to:

• Strict grounding of AI outputs in trusted systems of record.
• Fine-grained access controls so agents see only what they should.
• Human-in-the-loop workflows for high-risk outputs (e.g., financial advice, medical suggestions, legal communications).

Trust will be the differentiator between AI experiences that delight and those that harm brand equity.

How IT pros should think about next steps

For most organizations, the Bundesliga’s Captain should be viewed as aspirational but certainly doable. Practically, IT pros can start by:

• Identifying one high-value, data-rich customer journey (e.g., onboarding, troubleshooting, order tracking) as a pilot.
• Standing up a modest but modern data foundation for that journey, including event streaming and a unified view of context.
• Prototyping an AI companion that combines retrieval-augmented generation with a couple of simple agents (for routing and follow-ups).
• Instrumenting everything—latency, cost, satisfaction, containment—to build the business case for expanding to more journeys.

The Bundesliga shows what happens when an organization treats AI not as a feature but as a new way to connect with fans. IT leaders who treat generative and agentic AI as central to their customer experience strategy will be the ones who turn their own data into genuine customer devotion.