Formula 1 (F1) engages an audience of over 800 million fans globally across digital platforms, F1 TV, ticketing, and merchandise. Behind the scenes, F1’s MarTech platform, Customer 360, captures interactions across all touchpoints to power personalization and commercial strategy. However, the platform faced a massive operational challenge. According to Chris Roberts, Director of IT at Formula 1, integrating each new data source required 6 to 8 weeks of manual engineering, resulting in an 18-month backlog just to integrate 12 new sources.
To address this, Matt Kemp, F1 Head of Data Operations, set out to build a repeatable, robust, and reliable pipeline. In early 2026, F1 and #AWS collaborated to develop the Data Accelerator, an agentic AI solution built on Amazon Bedrock AgentCore. This transformed F1's MarTech data platform from a manually maintained system into a self-managed, observable, and unified data estate.
The Data Accelerator reduced data source onboarding from up to 8 weeks to approximately 40 minutes of automated code generation plus a few hours of deployment. It automatically identifies and fixes data source anomalies in production, tracks data platform operations and agent lineage in a single window, and enables seamless collaboration among analysts, engineers, and scientists.
Previously, onboarding was heavily manual: engineers wrote schema mappings, built ingestion pipelines, configured quality checks, and defined GDPR classifications by hand. Upstream providers frequently changed column names or restructured payloads without notice, breaking downstream systems. By utilizing agentic workflows on AWS, F1 now automates these complex steps, applying business logic dynamically at every stage of the pipeline.
[AgentUpdate Depth Analysis] The partnership between F1 and AWS highlights a pivotal shift in modern #DataOps: the transition from rigid, manual ETL pipelines to dynamic, self-healing, agentic data pipelines. By deploying Amazon Bedrock AgentCore, F1 solved a classic enterprise challenge—the data ingestion bottleneck caused by fluctuating schema designs and upstream changes. Unlike traditional low-code automation, agentic AI introduces semantic reasoning, enabling the platform to understand data context, perform real-time code generation, and execute autonomous anomaly recovery. This represents a paradigm shift for the AI Agent ecosystem, proving that agents are moving beyond simplistic chatbot interfaces toward becoming robust, enterprise-grade back-office operators. The ability to guarantee data integrity and track lineage in complex environments will likely make agentic DataOps a gold standard for digital-first organizations looking to unlock real-time business value.
