F1's AWS agentic AI cuts data onboarding from 8 weeks to 40 minutes

Formula 1, which engages 800 million fans across digital platforms, F1 TV, social media, ticketing, and merchandise, was drowning in data integration work. Its Customer 360 MarTech platform ingests feeds from ticketing partners, streaming services, sponsors, social media, and merchandise systems. But every new data source required 6-8 weeks of manual engineering, leading to an 18-month backlog for just 12 sources. According to Chris Roberts, F1's Director of IT, the MarTech platform is "the nervous system of fan engagement," yet fragmented visibility and brittle pipelines made it nearly impossible to keep pace with evolving upstream feeds—especially during race weekends and campaign launches.

In early 2026, F1 and AWS built the Data Accelerator, an agentic AI solution running on Amazon Bedrock AgentCore. It uses five workstreams: agentic data source onboarding (a Business Requirements Document yields a production-ready pipeline, including infrastructure code and transformations), automated schema evolution detection and remediation, unified data access through Amazon SageMaker Unified Studio, end-to-end observability with root cause analysis and context graphs, plus automated identification of failures that can be fixed via code. The result: onboarding drops to roughly 40 minutes of code generation plus a few hours of deployment, and F1 now has full data lineage, end-to-end visibility, and a collaborative environment for analysts, engineers, and scientists—no more dashboards full of ambiguous alerts.