How OneAdvanced deployed over 50 AI agents on UK-sovereign AWS
Not a pilot. OneAdvanced deployed 50+ AI agents in production on UK-sovereign AWS—here's the stack.
Why it matters
A real deployment case study showing how enterprises are moving agents from proof-of-concept to production at scale, with specific choices around sovereign compute, open-weight models, and agent orchestration frameworks.
The key facts
13 to know50+ agents deployed in production
Self-hosted Llama 4 Maverick on Amazon SageMaker AI (open-weight model choice)
UK-sovereign deployment requirement (regulatory constraint driving architecture)
RAG pipeline on pgvector (vector DB choice)
Strands Agents SDK for agent orchestration
Amazon ECS for agent runtime
Enterprise software provider (vertical: UK regulated market)
Self-hosted Llama 4 Maverick + Llama Guard 4 on Amazon SageMaker
RAG pipeline on pgvector
Agents built with Strands Agents SDK
Orchestrated on Amazon ECS
UK-sovereign compliance requirement
OneAdvanced: UK enterprise software provider
Go to the source
AWS Machine Learning Blogaws.amazon.com
Publisher excerpt: Learn how OneAdvanced, a UK enterprise software provider, built a UK-sovereign AI platform by self-hosting Llama 4 Maverick and Llama Guard 4 on Amazon SageMaker AI, with a RAG pipeline on pgvector and over 50 agents built with Strands Agents SDK on Amazon ECS.