From weeks to minutes: How Formula 1 uses agentic AI on AWS to accelerate data operations
Amazon Web Services
Formula 1, with the help of AWS, implemented the Data Accelerator, an agentic AI solution on Amazon Bedrock AgentCore, which reduces data source onboarding from 6-8 weeks to 40 minutes of code generation plus hours of deployment. The solution automates schema evolution, provides unified data access and observability, and handles 95% of onboarding work autonomously.
Formula 1's MarTech platform, Customer 360, faced operational challenges with onboarding new data sources, which took 6-8 weeks of manual engineering per source. In early 2026, F1 and AWS built the Data Accelerator using agentic AI on Amazon Bedrock AgentCore. The solution reduces onboarding time to approximately 40 minutes of code generation and includes five workstreams: agentic onboarding, automated schema evolution detection, unified data access via SageMaker Unified Studio, end-to-end observability with root cause analysis, and automated failure identification. Agents generate configuration files, infrastructure code, and governance policies automatically, including GDPR classification. The system handles 95% of onboarding work autonomously and resolves schema changes in hours instead of days. The observability layer provides full data lineage and causal root cause analysis, improving visibility and collaboration across teams.
- Abbreviations
- AWS = Amazon Web Services — Amazon Web Services
- GDPR = General Data Protection Regulation — Общий регламент по защите данных
- S3 = Simple Storage Service — Simple Storage Service
- BRD = Business Requirements Document — Документ с бизнес-требованиями
- PR = Pull Request — запрос на включение кода
- RCA = Root Cause Analysis — анализ корневых причин
Source: AWS ML blog —
original