InfoQ Homepage Azure Content on InfoQ
-
Microsoft Three-Layer LLM Routing Architecture for AI Agents on AKS
Microsoft has released a reference architecture for routing agent traffic on Azure Kubernetes Service. It breaks down the issue into three key choices: which model answers a call, how the call is managed, and which GPU replica handles it.
-
Claude Reaches GA on Microsoft Foundry: European Enterprises Cannot Deploy It
Claude models reached GA on Microsoft Foundry with Azure-native billing and governance, but no European data zone exists. Anthropic's own documentation confirms data residency guarantees apply to Bedrock and Vertex AI but not Foundry. European practitioners from banking and healthcare report the offering is unapproved for production.
-
Building a European Cloud Orchestration Platform within an Enterprise
Modern cloud deployments involve many tools with different lifecycles, creating a heavy burden on engineers. The Kubernetes ecosystem offers a unified Control Plane approach. Sharing best practices through tech talks and inner-source collaboration can create an engaged community and drive adoption.
-
Microsoft Expands Azure Kubernetes Service with Bare Metal, Fleet Management and AI Infrastructure
At this year's Microsoft Build 2026, Microsoft unveiled a broad set of enhancements to Azure Kubernetes Service (AKS) aimed at making Kubernetes a first-class platform for AI training, inference, and large-scale cloud-native applications.
-
Azure API Management Ships Unified Model API and MCP Content Safety at Build 2026
Azure API Management shipped a Unified Model API that lets clients speak one format while APIM transforms requests to Anthropic, Vertex AI, and other backends. Content safety policies now cover MCP tool calls and Agent-to-Agent payloads alongside LLM traffic. Token metrics expanded to track reasoning, cached, and audio tokens across providers.
-
Microsoft Launches Logic Apps Automation at Build 2026
Microsoft announced Logic Apps Automation at Build 2026, a new SKU at auto.azure.com packaging workflows, AI agents, knowledge services, and model access into a managed SaaS experience. Agents integrate via agent-loop orchestration, Foundry agents, and managed sandbox. Knowledge as a Service provides a fully managed RAG pipeline.
-
Azure Logic Apps Adds Sandboxed Code Interpreters to Agent Workflows
Microsoft added sandboxed code interpreters to Azure Logic Apps, enabling agents within integration workflows to generate and execute Python, JavaScript, C#, and PowerShell in Hyper-V isolated sessions. Architects get full control over model selection per workflow. The capability positions Logic Apps as an agent platform for integration alongside Foundry and Copilot Studio.
-
Microsoft Launches Azure Copilot Migration Agent to Accelerate Cloud Migration Planning
Microsoft has launched the Azure Copilot Migration Agent, an AI assistant built into the Azure portal that automates migration planning, agentless VMware discovery, and landing zone creation. Despite being billed as generally available, the agent is in public preview and cannot execute migrations. Replication and cutover remain manual tasks in Azure Migrate.
-
Microsoft Adds DRA-Backed NVIDIA vGPU Support to AKS
The Azure Kubernetes Service team shared a detailed guide on how to use Dynamic Resource Allocation (DRA) with NVIDIA vGPU technology on AKS. This update improves control and efficiency for shared GPU use in AI and media tasks.
-
QCon London 2026: Your Multi-Cloud Strategy Is a Product Problem — Treat It Like One
JP Morgan Chase engineers Luis Albinati and Surabhi Mahajan argued that multi-cloud complexity can't be solved with engineering alone. Speaking at QCon London, they showed how treating multi-cloud as a product with capability mapping, demand governance, and defined users tames the chaos.
-
QCon London 2026: How to Run on Three Clouds at Once, and When Not to
Form3 runs UK bank payments across three clouds simultaneously. At QCon London, their engineers explained how they built their custom Kubernetes operators, cross-cloud DNS tricks, and distributed databases, and what happened when they tried to sell them in America. Spoiler: US customers wanted East/West failover, not triple-active multi-cloud.
-
Claude Opus 4.6 Introduces Adaptive Reasoning and Context Compaction for Long-Running Agents
Anthropic’s Claude Opus 4.6 introduces "Adaptive Thinking" and a "Compaction API" to solve context rot in long-running agents. The model supports a 1M token context window with 76% multi-needle retrieval accuracy. While leading benchmarks in agentic coding, independent tests show a 49% detection rate for binary backdoors, highlighting the gap between SOTA claims and production security.
-
Running Ray at Scale on AKS
The Azure Kubernetes Service (AKS) team at Microsoft has shared guidance for running Anyscale's managed Ray service at scale. They focus on three key issues: GPU capacity limits, scattered ML storage, and problems with credential expiry.
-
OpenAI Scales Single Primary PostgreSQL Instance to Millions of Queries per Second for ChatGPT
OpenAI described how it scaled PostgreSQL to support ChatGPT and its API platform, handling millions of queries per second for hundreds of millions of users. By running a single-primary PostgreSQL deployment on Azure with nearly 50 read replicas, optimizing query patterns, and offloading write-heavy workloads to sharded systems, OpenAI maintained low-latency reads while managing write pressure.
-
Microsoft Releases Azure Functions Support for Model Context Protocol Servers
Microsoft has launched its Model Context Protocol (MCP) for Azure Functions, ensuring secure, standardized workflows for AI agents. With built-in OBO authentication and streamable HTTP transport, it addresses key security concerns. Now supporting multiple languages and self-hosting, MCP empowers developers to deploy with ease while safeguarding sensitive data.