How OneAdvanced deployed over 50 AI agents on UK-sovereign AWS
TL;DR
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.
Nauti's Take
For small teams, the first checkpoint is data control: which documents may enter the pgvector RAG layer, who can start an agent, and where is every access logged? Before copying a 50-agent setup, test one workflow with real permissions and measure whether the added control justifies the operational overhead.
Video
Sources
