Browse Artificial Intelligence Community (139)

isaiahhoyer describes using Microsoft Discovery agents to adapt Microsoft Premonition biological monitoring systems for citrus pests. The case study covers grounding agents in engineering documents, designing field experiments, preparing permit requests, and generating synthetic wingbeat data for preliminary edge classifiers, with scientific review and human oversight throughout.

MinseokSong explains how production failures shaped translation review in Co-op Translator. Rather than relying on quality scores or model verdicts alone, the project checks document structure, preserves human edits where possible, and records unresolved failures. The approach gives reviewers concrete checks while leaving meaning, terminology, and readability to human review.

Ben Sickle outlines Microsoft’s announcements at NVIDIA GTC Berlin 2026 focused on running AI across Azure and customer-controlled environments, including Azure Local sovereign deployments, Foundry Local for on-prem model inference, confidential VMs, open-model endpoints for NVIDIA Nemotron via Fireworks AI on Azure, and GPU-accelerated analytics in Microsoft Fabric.

DivSwa explains how to move off Microsoft Foundry workflows (retiring Dec 1, 2026) by orchestrating Foundry Prompt Agents and Hosted Agents inside Azure Logic Apps, combining event-driven triggers and connectors with deterministic workflow steps around agent calls.

naafiahsadique introduces Azure Copilot for Azure Local, an AI-powered, agentic troubleshooting experience aimed at helping operators investigate and resolve issues across distributed Azure Local infrastructure using natural-language questions and guided, multi-step diagnostics.

sonjagu rounds up the October updates for Azure SRE Agent, including new security and data residency guidance, enterprise deployment resources, GitHub Copilot Canvas collaboration, and new extension patterns like private Splunk MCP samples, Azure DevOps repo-backed plugin distribution, and ServiceNow response plans.

Stuart Russell outlines new and upcoming controls for Microsoft Sovereign Public Cloud and how they map to real Azure workload stages (data, indexing, inference, telemetry). The post covers Sovereign Control Panel, operator-access evidence features, key custody options with Managed HSM, confidential computing, and updated Sovereign Landing Zone implementations with Bicep and Terraform.

insagiv outlines how Foundry Local (GA on Azure Local) targets “sovereign AI” scenarios by running supported models in customer-controlled environments, including disconnected setups. The post covers local inference, model management, OpenAI-compatible APIs, retrieval with citations, early agent/connector capabilities via MCP, and how GitHub Enterprise Local supports SDLC sovereignty.

sushil_jarwal announces GitHub Enterprise Local and explains how it brings GitHub Enterprise Server-style source control and workflows to customer-controlled Azure Local environments. The post highlights a guided Azure deployment flow using Workload Orchestration, storing deployment secrets in Azure Key Vault, and AI options ranging from GitHub Copilot (connected) to Foundry Local models (restricted/disconnected).

meenagowdar outlines new capabilities for Microsoft Sovereign Private Cloud built on Azure Local, including Foundry Local for running AI models on-premises, options for connected vs disconnected operations, confidential VMs for sensitive workloads, and GitHub Enterprise Local to keep repos and CI/CD inside a sovereign boundary.

Krishnaprasad Hande explains a reference architecture for running sensitive AI inference on shared Azure GPU capacity using Azure Confidential Computing, NVIDIA H100 confidential GPUs, and Protopia’s Stained Glass Transform, with attestation and key-release controls to reduce data exposure across the inference path.

kinfey explains how to add per-turn model routing to GitHub Copilot CLI and the VS Code Copilot extension without replacing the native Copilot experience. The post introduces Microsoft-Decision-1 in Azure AI Foundry as a fast “decision model” for structured scoring, then shows how to apply policy, privacy boundaries, and model pinning across tool continuations.

robertocarli outlines five practical scenarios where Microsoft Web IQ helps AI agents use up-to-date web evidence, so answers are sourced, current, and more reliable for real business workflows like research, customer support, shopping assistance, compliance checks, and sales preparation.

robertocarli introduces Microsoft Web IQ, an Azure-billed web search and grounding API designed for AI agents and RAG apps, and explains how it delivers fresh, citable web evidence with low latency using Bing’s web substrate, Harrier embeddings, DiskANN indexing, and structured passage-level results.

tokawa-ms reports a reproducible Windows CP932 encoding bug in Microsoft Discovery App Preview (0.15.19) where Bookshelf Ask/ask_content using the GraphRAG Zero provider returns an empty answer despite successful retrieval and logged answer generation, due to a UnicodeEncodeError and poor failure propagation.

abhilashasr threat-models Azure MCP Server for AI-assisted incident response, focusing on how Entra ID, Azure RBAC, Key Vault, Policy, and monitoring controls prevent an assistant from turning diagnostics into unintended production changes. It also includes a read-only demo connecting GitHub Copilot in VS Code to Azure Monitor and Log Analytics.

RicardoDuncan rounds up the latest SQL developer tooling updates for VS Code, including new MSSQL extension features, GitHub Copilot schema-aware agent workflows, and Microsoft SQL “skills” for assessing and migrating SQL Server to Azure SQL, plus driver releases aligned with SQL Server 2025.

kinfey explains how to use small language models (SLMs) as typed “decision components” inside an application, then walks through a concrete pipeline using Microsoft Olive to LoRA fine-tune Qwen3.5-0.8B, export to CUDA FP16 ONNX, and validate decisions via option-letter probabilities.

dchelupati explains how to scale Azure SRE Agent from a single team to enterprise-wide use, focusing on access control, guardrails, auditing, multi-agent topologies, and “agent as code” practices for repeatable deployment and governance.

dchelupati shares a practical “start small” adoption guide for Azure SRE Agent, focused on picking a first operational use case, connecting only the required context (telemetry, repos, runbooks), and expanding into repeatable workflows with the right triggers and permissions.

paulyuk shows how the Azure SRE Agent canvas fits into GitHub Copilot (App and Copilot CLI) so on-call engineers can validate an agent’s incident diagnosis with their own telemetry, queries, and access controls, then share a reviewed update back to the team.

sdighe explains how large-scale AI training and inference are pushing datacenter networks to evolve, and why networking now needs to be designed as part of the AI system. The post highlights open specifications like Multipath Reliable Connection (MRC), plus industry efforts around optical interconnects and Ethernet scale-up networking.

mariozeng explains how Microsoft is rethinking power delivery for Azure AI infrastructure, focusing on grid-to-chip efficiency for high-density GPU systems. The post covers LVDC and 800VDC distribution, disaggregated rack power (Mt. Diablo), solid-state transformers with energy storage, and server-to-silicon power delivery design.

Wuyi Weng shows how to run Qwen3.8-Flash-Next across two H100 GPUs on an Azure Spot VM, then instrument and troubleshoot it with OpenTelemetry, Application Insights/Azure Monitor, and Grafana. The post focuses on KV-cache behavior under agentic load, dashboard pitfalls, and a vLLM KV-cache FP8 setting that improves concurrency and time-to-first-token.

GisliGudmundsson shares a reference pattern for running Azure AI Foundry workloads inside a secure Azure landing zone, using private endpoints and private DNS zones, disabling local auth in favor of managed identity, and placing Azure API Management in front to enforce token limits and emit token usage metrics.

Rama Bhimanadhuni explains how Microsoft is working with the Open Compute Project (OCP) and major hardware vendors to standardize reliability and manageability for large, multi-vendor AI clusters, focusing on RAS signals, diagnostics, telemetry, and safer firmware update workflows to keep fleet capacity and availability high.

Wuyi Weng shares a practical, numbers-driven guide to self-hosting the Qwen3.8-27B model on an Azure H100 Spot VM, including the exact vLLM serving flags, a Docker Compose deployment, and an end-to-end observability setup with OpenTelemetry, Application Insights, and Grafana to decide when Spot hosting breaks even.

Brittany Pugh lays out a production-minded reference architecture for document-heavy intake on Azure, showing how to put AI behind a governed API gateway, process work asynchronously, and keep an end-to-end audit trail with a single correlation ID across API Management, Service Bus, Functions, and Event Grid.

santiagxf announces a public preview integration that connects Microsoft Agent 365 governance with Azure API Management runtime enforcement for MCP servers and tools, adding optional threat and data protection checks via Microsoft Defender and Microsoft Purview.

DivSwa announces public preview pricing and monthly free grants for Azure Logic Apps Automation, including what’s covered (managed environment, workflow runtime, retention, connectors, AI usage, knowledge storage, and isolated code execution) and how to track and keep eligibility for the free environment.

bobmital announces the general availability of Anyscale on Azure, a managed Ray runtime that runs on Azure Kubernetes Service in the customer’s subscription. The post explains the control-plane/data-plane split, Azure-native identity and governance integration, private connectivity options, and the kinds of AI/ML workloads teams can run end-to-end.

kinfey breaks down what changes when an AI agent can run tools and create side effects, then shows how to put real execution boundaries around those tools using OpenSandbox on AKS with Kata pod VMs, plus a comparison to Azure Container Apps Sandboxes and Dynamic Sessions.

Sonia Cuff’s September 2026 FinOps roundup pulls together cost and pricing updates across Microsoft’s AI and cloud stack, including Azure AI Foundry and Azure OpenAI pricing changes, new model options, and GitHub Copilot billing/usage metrics updates, plus a few Azure cost-optimization and purchasing notes.

simonjj explains when “decision models” are a better fit than general-purpose LLM calls, then benchmarks a self-hosted Winnow model served by Ollaya on Azure Container Apps serverless GPU against GPT-5.4 Nano via Azure OpenAI, focusing on latency, throughput, accuracy, and token usage trade-offs.

frrey explains how Azure ExpressRoute and Microsoft’s AI Points of Presence (AI PoPs) are used to connect distributed, third-party GPU capacity to Azure with private networking, aiming to keep a consistent Azure operating model even when compute runs outside hyperscale regions.

Rebekah Midkiff lays out a reference architecture for governing AI agents across multiple Microsoft Entra tenants, combining Agent 365, Entra Agent ID, Microsoft Foundry, Copilot Studio, Purview, and an Azure API Management AI gateway to enforce identity, policy, tool access, and observability at runtime without collapsing tenant boundaries.

rickliev outlines Microsoft’s message for TM Forum Innovate Americas 2026: scaling agentic AI in telecom depends on trusted, governed data plus shared operational context. The post connects “agent-ready” data concepts (meaning, provenance, permissions) with Microsoft Fabric capabilities like OneLake, Fabric IQ, and Real-Time Intelligence.

kinfey describes a hands-on experiment comparing a traditional GitHub Copilot tool-calling agent loop with a Jev-based “decision harness” that produces typed choices and confidence signals before execution. The post focuses on splitting responsibilities between models and ordinary code to reduce unnecessary model work and improve observability.

Christine Caggiano explains how a multidisciplinary team used the Microsoft Discovery app to design an inspectable, reproducible bioinformatics workflow for phage therapy—connecting curated literature, genomic analysis, and external tools via MCP-based adapters, with validation steps and safety checks built into each stage.

paulyuk introduces the Azure Functions Hosted Skills canvas inside the GitHub Copilot app, showing how to build and test an event-driven Function App locally, invoke triggers on demand, and debug runs with logs and evidence links. The post also covers deployment to Azure with azd and exposing skills as MCP tools.