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
More than 50 agents on a sovereign AWS platform is useful evidence that agent operations work with documented data control rather than only on slides. The catch is operational cost, since permissions, logging and approvals scale with every additional agent.
Small teams should test one workflow with real permissions and measure whether the added control justifies the overhead.
Video
Sources
