AI Knowledge Base · AI Cloud Platforms · Hyperscalers
Microsoft Azure
Azure OpenAI and AI Foundry, wired into Microsoft 365 and Entra ID.
Best for: Microsoft-centred organisations that want OpenAI models with enterprise identity, compliance and Copilot integration.
AI services
- Azure OpenAI in Azure AI Foundry: OpenAI's GPT and reasoning models, plus a catalogue of open and partner models.
- Foundry Agent Service for building and running agents; Azure AI Search for retrieval.
- Azure AI Content Safety and evaluation tools; Azure Machine Learning for custom training.
GPUs and accelerators
- ND H100 v5, ND H200 v5 and ND GB200 v6 virtual machines with InfiniBand.
- AKS with GPU node pools; AMD MI300X options.
Agents and identity
- Microsoft Entra ID with managed identities and workload identity; Entra Agent ID for agent identities.
- Conditional Access and Privileged Identity Management for administrators.
Security and data
- Private endpoints and network isolation for AI resources; customer-managed keys.
- Content filters and prompt shields against jailbreaks and indirect prompt injection.
- Defender for Cloud and Purview for AI posture and data governance.
Scaling and optimisation
- Provisioned throughput units (PTUs) for predictable latency; global and data-zone deployments to spread load.
- Batch API for large offline jobs at lower cost.
UK and EU regions
UK South and UK West, with EU data-zone deployments.
Watch out for
Model availability and quota differ by region and deployment type; reserve PTUs early for launches.
How Workstation helps: We deploy Azure OpenAI and Foundry agents with Entra identity, private networking and Microsoft 365 integration.
Scaling AI at large scale with Amazon Bedrock →CI/CD for LLMs, agents and data in the cloud →Securing LLM and agent APIs →The AI agent harness →Identity and authentication for AI →
Other providers we work with
Logos are trademarks of their respective owners, used only to identify each platform, and come from Wikimedia Commons. Diagrams by the Workstation team.