Formula 1 cuts data integration from 8 weeks to 40 minutes with AI agents on AWS

In early 2026, Formula 1 and AWS built the Data Accelerator to transform F1's Customer 360 MarTech platform from a manually maintained system into a self-managed, observable, and unified data estate. F1's platform ingests data from ticketing partners, streaming integrations, sponsor activation feeds, social media, and merchandise systems to power personalization, segmentation, and commercial strategy for an audience of over 800 million fans. Races happen every two weeks, and fan engagement windows are measured in minutes—commercial decisions need to move at the speed of the grid.

The operational challenge was acute. According to Chris Roberts, Director of IT at Formula 1, every new data source required 6 to 8 weeks of manual engineering, and the team had an 18-month backlog just to integrate 12 new sources. Matt Kemp, F1 Head of Data Operations, explained the problem: "Manually ingesting data sources is time consuming, creates solution variances, and ultimately results in data integrity issues." The business was generating data faster than engineers could wire it up. On top of onboarding delays, upstream providers frequently changed column names, added fields, or restructured and rescheduled payloads without notice. These changes often surfaced at the worst moment—mid-race-weekend or during a mission-critical campaign launch. Meanwhile, visibility was fragmented: logs were scattered across services with no unified data lineage, so when a stakeholder questioned a metric, engineers spent hours manually tracing the issue across Amazon S3 paths, Amazon Redshift control tables, Airflow logs, and DBT outputs.

The Data Accelerator addressed these challenges through five simultaneous workstreams. The centerpiece is agentic data source onboarding using Amazon Bedrock AgentCore. The system works in two phases: Phase 1, a team member uploads a Business Requirements Document to an S3 bucket, triggering an AWS Lambda function that invokes Amazon Bedrock AgentCore Runtime. The agent reads the BRD and generates a set of configuration files, then accesses GitHub through a GitHub App to push these files as a pull request to a standardized Git repository and accesses Jira through its REST API to create a ticket. An engineer reviews and approves. Phase 2, the agent takes the approved configuration and generates three separate pull requests: AWS Glue application and infrastructure code, DBT transformation framework, and governance policies including GDPR tagging. All three PRs link to a single Jira ticket for traceability. What distinguishes this from a basic code generator is the integrated GDPR classification: the agent proactively analyzes every data column, determines whether it contains personal data, sensitive personal data, or pseudonymized data, and tags it with the appropriate GDPR category. These tags publish directly to the governance registry in SageMaker Unified Studio, giving the compliance team immediate visibility without manual review cycles. The modular skill architecture encapsulates distinct capabilities—schema mapping and data type inference, data quality validation, governance enforcement, and sensitive data classification—as separate skills that activate at runtime. The agent uses a multi-pass reasoning process: Pass-0 handles token management, Pass-1 summarizes tool outputs, and Pass-2 rolls up an overall assessment. The result is onboarding time dropped from 6 to 8 weeks to approximately 40 minutes of code generation plus hours of deployment and review, with AI agents handling 95% of the work autonomously.

Automated schema evolution detection is the second workstream. The same agent architecture that handles onboarding now continuously monitors for upstream schema changes using event-driven triggers with AWS Lambda and Amazon EventBridge. When a provider modifies their data structure, the agent detects it, assesses the downstream impact by identifying which pipelines are affected and which consumers depend on the changed fields, and then generates the necessary code updates across all affected repositories and creates a Jira ticket with full context and linked PRs. End-to-end resolution now takes hours instead of days. The third workstream, unified data access through Amazon SageMaker Unified Studio, transformed how teams collaborate. Previously, data engineers curated pipelines in one account, data scientists modeled in a separate account, and analysts operated in a third world entirely. Nobody shared tooling or context, and getting from a question to an answer took days of coordination. The solution uses SageMaker Unified Studio as the foundation for a data mesh framework where declarative governance codifies access control. A single data source definition simultaneously publishes data to the catalog and provisions the access control needed for consumers to subscribe, making it safe for agents to onboard new data products end-to-end without human review of IAM policies. Data scientists now open Unified Studio, find curated Customer 360 datasets, and start modeling with shared notebooks, consistent tooling, and governed access—the curation and consumption finally live side by side.

The fourth workstream delivered end-to-end observability with a root cause analysis tool and context graph. The observability layer presents full data lineage from S3 raw ingestion through processed layers into Amazon Redshift DBT stages as a single interactive graph, color-coded for health. Users click on any node to drill down to individual sources and tables, each showing pass/fail status, last run time, and duration. If a pipeline fails, the lineage visualization shows exactly where the break occurred and which downstream data is affected. Root cause analysis (RCA) reads system logs and identifies failure points across the data estate. Roberts reflected on the impact: "For the first time, we have end-to-end visibility across the entire MarTech platform with data lineage and root cause analysis, not just dashboards full of alerts." A sixth workstream optimized the customer identity resolution algorithms that unify fan touchpoints across channels.