Browse All Artificial Intelligence Content (824)

John Savill explains what an agent control plane is and why it matters when you start running AI agents at scale, focusing on the need for centralized oversight, evaluation, and cost governance.

This week's AI roundup centers on making agent work more verifiable, governable, and ready for production. Microsoft introduced Web IQ to bring citation-ready web grounding into agent toolchains, while GitHub and VS Code expanded agent surfaces, model choice, and the admin controls needed to keep policy enforceable. On the security and operations side, GitHub Advanced Security shipped AI Scan for PRs and agentic autofix to GA, and Azure MCP Server 3.0 plus new threat modeling guidance underscored that identity, RBAC, and audit trails matter more as agents start changing real systems. We also saw Foundry add routing and observability primitives, new patterns for memory and planner-executor loops, and deeper infrastructure context around Maia 300 and the power and networking constraints behind large-scale inference.

John Edward explains when multi-agent systems are worth the added complexity, and how to design them so they stay predictable, secure, and testable. The article breaks down common orchestration patterns, communication/state design, guardrails, and practical evaluation metrics for cost, latency, and accuracy.

Sameen Karim explains how GitHub uses a swarm of AI agents to stress test new features before release, with agents continuously probing for edge cases and attempts to circumvent rules to help harden the system.

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.

GitHub demonstrates the My AI Usage Canvas, a custom dashboard built around Copilot Chronicle commands to help developers visualize token consumption, see which AI models they use most, and understand usage patterns across repositories to identify practical ways to reduce AI costs.

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.

sbaynes interviews Mercedes-AMG PETRONAS F1 lead race strategist Joey McMillan on how the team uses Microsoft Azure—especially Azure Batch—to run large-scale race simulations quickly enough to influence live, race-day strategy decisions under changing weather and track conditions.

Michael Scovetta summarizes Microsoft and NVIDIA’s guidance on managing risk when deploying open-weight AI models, focusing on how risk depends on the model, use case, deployment architecture, and safeguards, and how to connect risk categories to evaluations and controls.

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.

John Savill shares a short Azure Weekly Update for 16 October 2026, covering a handful of platform changes across resiliency, compute, networking, storage, and Azure’s AI hardware/model announcements.

Fokko at Work demos selected new features in Visual Studio Code 1.142 with a focus on GitHub Copilot and related UI changes, including canvases and the redesigned model picker, plus workflow improvements like moving chats between folders and worktrees.

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.

Allison announces updates to GitHub Copilot in Slack and Microsoft Teams, including multi-repo support in a single conversation plus improvements to mentions, repository switching, Slack thread context, and overall reliability.

Nick Brady’s September 2026 roundup covers Microsoft Foundry updates across models, agents, observability, and tooling—highlighting GPT-6 family GA, Routines and Tool Search GA, Insights preview, Model Router preview controls, and Foundry Local 2.1 bring-your-own-model support with ONNX Runtime GenAI.

GitHub demonstrates how the Logitech MX Keypad integrates with the GitHub Copilot app to control Copilot Chat and voice prompts from dedicated hardware keys, plus manage projects, sessions, and MCP server toggles without leaving the coding flow.

Martin Woodward explains how GitHub Copilot’s agentic workflows are shifting development from issuing commands to expressing intent, and why “ambient intelligence” needs strong context, clear boundaries, and developer control. He also shares a practical example: mapping Copilot actions to physical controls like the Logitech MX Keypad.

Allison announces a November 16, 2026 deprecation of several AI models across GitHub Copilot experiences, and explains what admins and teams need to do to keep Copilot Chat, agent modes, and other Copilot features working with supported alternatives.

Microsoft Developer presents a Data Exposed session on Fabric Database Hub, focusing on bringing Azure SQL, SQL Server, Cosmos DB, PostgreSQL, and Fabric databases into a single place for discovery, estate-level visibility, governance, and AI-assisted insights to prioritize actions.

Mike Hulme explains how Azure is evolving its cloud-native platform to better support AI workloads and AI agents, focusing on coordinated compute/storage/networking, production-ready open-source foundations (notably Kubernetes), cost governance with FinOps, and “agentic” operations to improve reliability and efficiency at scale.

Lim Ai Leen reports on Bar-Ilan University’s pilot of an AI agent in Moodle that helps students search, summarize, and quiz themselves on course materials using natural language, built with Azure AI Services and Microsoft Copilot Studio and run in the university’s Azure environment.

Allison announces general availability of GitHub’s AI Scan for pull requests, an AI-powered code scanning capability that complements CodeQL by detecting vulnerabilities in PR changes (including languages and file types CodeQL may not cover) and surfacing advisory findings with explanations and suggested fixes.

Aaron Stark talks with Haishi Bai about Adaptive Applications, a capability-based architectural approach for building portable apps that can run across Azure, sovereign environments, edge, and on-premises. They focus on decoupling application needs (AI, data, identity) from the underlying services to meet compliance, residency, and continuity requirements.

Allison announces general availability of agentic autofix for GitHub code scanning alerts, where Copilot explores the codebase, proposes and validates fixes with CodeQL, and opens a draft pull request. The post also covers where it can be used, required policies and permissions, and how billing works with AI Credits and Actions minutes.

Eduard van Valkenburg explains how Microsoft Agent Framework for Python models and uses vector stores for embeddings, vector search, and agent context. The post shows how to define typed records, index and query data, expose vector search as an agent tool, and keep conversation history searchable via context providers across multiple database integrations.

John Edward explains an upcoming Microsoft Entra default-permission change that lets ordinary users create agent blueprints unless admins disable it. The post breaks down what’s changing, what isn’t, and the specific Entra admin center setting IT teams should review before the November 2026 rollout.

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.

John Edward explains the planner-executor loop as a practical architecture for building agentic systems on Azure, focusing on how to separate planning from execution, validate model outputs, and run tool calls safely. The article maps the pattern to Azure services and highlights reliability, observability, and access-control decisions needed for production use.

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.

Lee Murray explains how VS Code’s modernized UI preview evolved from the 2026 themes and the Agents window, and how developer feedback is shaping layout density, editor tabs, theming controls, and performance work in the workbench.

Sandeep Sen announces the stable Azure MCP Server 3.0 release and explains what’s new for bringing Azure operational tooling into MCP-compatible AI agent workflows, including Terraform and Advisor tooling, more predictable client integration, and security-focused defaults for resource creation.

Allison announces updates to HydraFusion in GitHub Copilot, including a refreshed frontier-model pool, improved Cascade and Critique orchestration workflows, and a new HydraFusion Max option for deeper reasoning on demanding tasks across VS Code, the Copilot app, and Copilot CLI.

Jakub Oleksy reports on GitHub’s September 2026 reliability work and incidents, including database pressure reductions, overload controls, added headroom for GitHub Actions, expanded failure containment for pull requests, and progress moving production workloads and traffic to Azure.

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.

The Visual Studio Code Team shares early release notes for VS Code 1.143 Insiders, highlighting updates to MCP server configuration, Agent Host chat controls for background shells, and a new extension contribution point for Explorer title actions.

Microsoft Developer demonstrates an end-to-end workflow for building and shipping a hosted AI agent from the terminal using GitHub Copilot CLI and Microsoft Foundry, including planning, resource creation, model selection, evaluation-driven improvements, and a secure Azure Functions proxy to connect the agent to a website chat experience.

Joe Filcik and Colin Murphy explain how Azure Content Understanding uses grounding and field-level confidence to make document extraction results inspectable and actionable, then show how to calibrate confidence thresholds (per document type and per field) to route work in human-in-the-loop review workflows.

James Rempt shares takeaways from VSLive! San Diego on how experienced Visual Studio developers are adopting GitHub Copilot and other AI tools, while spending more time validating generated code and leaning on hands-on learning. The post also highlights how Visual Studio Subscription benefits support ongoing skill-building.