← Back
AWS ML Blog

How OneAdvanced deployed over 50 AI agents on UK-sovereign AWS

13 min read
#agents#deployment#llm#amazon
Level:Advanced
For:AI Engineers
TL;DR

OneAdvanced, a UK-based enterprise software provider, successfully deployed over 50 AI agents on a UK-sovereign AWS architecture, ensuring data sovereignty and compliance with strict regulations. The solution utilizes Llama 4 Maverick and Llama Guard 4 models, self-hosted on Amazon SageMaker AI, and pairs a Retrieval Augmented Generation (RAG) pipeline with Amazon Aurora PostgreSQL-Compatible Edition and the pgvector extension. The architecture supports rapid agent deployment and content moderation, while maintaining control over model serving infrastructure. This approach enables OneAdvanced to meet the sovereignty requirements of their customers, particularly in highly regulated industries.

⚡ Key Takeaways

  • OneAdvanced deployed over 50 AI agents using Llama 4 Maverick and Llama Guard 4 models on Amazon SageMaker AI.
  • The solution utilizes a Retrieval Augmented Generation (RAG) pipeline backed by Amazon Aurora PostgreSQL-Compatible Edition with the pgvector extension.
  • The architecture runs on Amazon Elastic Container Service (Amazon ECS) with Strands Agents SDK.
  • The models are self-hosted on p5.48xlarge instances in the London (eu-west-2) region to ensure UK data sovereignty.
  • The solution supports ISO 42001 certification for AI governance.
💡 Why It Matters

This deployment demonstrates the feasibility of self-hosting large language models on AWS infrastructure to meet strict data sovereignty requirements, particularly in highly regulated industries. This approach enables organizations to maintain control over their model serving infrastructure while ensuring compliance with regulations.

✅ Practical Steps

  1. Deploy Llama 4 Maverick and Llama Guard 4 models on Amazon SageMaker AI using p5.48xlarge instances in a UK-based AWS region.
  2. Implement a Retrieval Augmented Generation (RAG) pipeline using Amazon Aurora PostgreSQL-Compatible Edition with the pgvector extension.
  3. Utilize Strands Agents SDK to develop and deploy AI agents on Amazon Elastic Container Service (Amazon ECS).

Want the full story? Read the original article.

Read on AWS ML Blog

More like this

Building an AI Text Detector From Scratch

Ahead of AI#llm

GLM-5.3 is here with advanced cyber capabilities — and reportedly already found a 'serious vulnerability' in Cursor

VentureBeat AI#llm

Custom reward functions for multi-turn reinforcement learning with Amazon Nova Forge

AWS ML Blog#amazon

RAG Workflow and Loop Engineering: The Dispatcher That Decides When to Loop and When to Stop

Towards Data Science#rag

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING