Browse All Posts (133)

Carlin Cherry explains how to prioritize Dependabot vulnerability alerts beyond severity alone. The short covers whether a dependency is used, whether an application can reach vulnerable code, and whether that code is exposed in production, combining these signals with severity and EPSS to guide remediation decisions.

Microsoft Threat Intelligence examines how Storm-3358 uses ARTEX to attack financial organizations, exploit web applications, and deploy remote access trojans. The report outlines behavioral signals, deception techniques, identity protections, and hunting queries for Microsoft Defender XDR and Microsoft Sentinel to help defenders investigate related activity.

Allison outlines updates to GitHub Copilot code review, including API-based settings management across enterprises, organizations, and repositories. The changes also add attribution and source metadata, compact review overviews, AI credit visibility, and reliability fixes. Administrators should note differences in token and GitHub App support across settings endpoints.

Allison explains how the GitHub Copilot impact dashboard now tracks Copilot Chat and VS Code Agents window engagement across nine experiences. Enterprise and organization reports include the same additions, while the renamed Chat-first users cohort, unchanged adoption phases, and reporting rules clarify how to interpret the metrics.

Nick Liffen outlines how GitHub Copilot can support planning, implementation, verification, and production investigation beyond code generation. The guide covers shared project context, parallel tasks, focused pull requests, security checks, and operational evidence, while keeping developers responsible for approving plans, evaluating changes, and deciding what needs to happen next.

Allison summarizes this week’s GitHub Copilot updates, including availability in JetBrains Air and a public preview in Xcode’s built-in coding assistant. Other changes cover pull request merging, conversation context limits, CLI settings, session organization, and VS Code tools for reviewing agent work and scheduling local tasks.

Allison announces general availability of @GitHub in Slack and Teams, letting developers investigate bugs, create issues, implement changes, and open pull requests from conversations. Canvas in Teams supports collaborative review of plans, changes, and previews, while additional updates simplify repository selection and improve conversation reliability and attribution.

Microsoft Developer summarizes this week’s updates: a public preview of Microsoft’s Copilot harness in Foundry Agent Service, authentication improvements in the October Azure SDK release, and a stable Cosmos DB client for Rust. The video also covers PIX crash postmortems for Windows games and the upcoming .NET Conf.

Martin Woodward demonstrates a custom 3D-printed pumpkin that monitors GitHub Actions credits. Powered by a microcontroller and addressable LEDs, it changes color as the account quota drains and animates when credits renew. This GitHub Podcast clip shows a playful hardware alert, with open-source code available on GitHub.

geometry outlines a practical reliability checklist for AI agents built with Microsoft Foundry. The article covers agent instructions, external tool contracts, evaluation datasets, Azure Application Insights monitoring, and security controls, using an order-support example to explain how teams can test failures and review changes before production deployment.

John Savill reviews this week's Azure updates across disaster recovery, networking, storage, databases, and AI. Topics include Service Bus geo-replication, post-quantum TLS key exchange, Application Gateway for Containers capabilities, SQL backup immutability, PostgreSQL networking changes, and Kimi K3.1 Pro in Foundry.

kedikala explains how to improve production agents in Microsoft Foundry using continuous evaluation, reviewed trace datasets, and Agent Optimizer. The workflow separates optimization from release testing, gates candidates in GitHub Actions, and uses controlled canary sessions to verify quality, cost, and transaction safety before promotion.

John Edward outlines three planned read-only diagnostics in Microsoft Purview eDiscovery for troubleshooting case access, security filters, and hold-policy distribution. The update is scheduled to roll out from December 2026 into early 2027, with separate government cloud timelines and no required changes to existing configurations.

John Edward explains why organizations should shorten the gap between Windows security update release and deployment as AI accelerates vulnerability analysis. He outlines how Windows Autopatch and hotpatching can help, alongside supported operating systems, security baselines, endpoint monitoring, and tested recovery procedures.

Qianqian Ye and John Maeda explore why sketching with code still matters when AI can generate functional output. Drawing on creative coding with p5.js and teaching at USC, they discuss how iteration builds the intuition to understand generated systems and exercise creative judgment rather than rely only on prompts.

Nick Chapsas introduces closed hierarchies, a new feature described as coming to C# 15 and .NET 11. He discusses how it addresses problems with inheritance in C# and why it can help developers and coding agents write safer code.

WSilveira explains the new .NET 10 custom-code support in Azure Logic Apps Standard and walks through migrating existing .NET 8 projects. The guide covers project dependencies, runtime settings, coordinated debugging, deployment verification, and an optional GitHub Copilot skill that assists with migration without rewriting workflows.

Allison outlines new GitHub Copilot usage metrics API fields that show whether developers act on code review feedback. Repository reports now include addressed rates, comment breakdowns, and merged pull requests without subsequent human change requests, with important distinctions around merge-day counting, bot pull requests, and report access.

Allison details new GitHub Copilot usage metrics API fields that identify missing client telemetry and IDE or extension version gaps. Enterprise and organization reports now show affected users and daily counts, with guidance on access permissions, overlapping counts, and interpreting unavailable data.

Khalid Abuhakmeh compares Blazor’s four web render modes and Blazor Hybrid, explaining where components execute and how each option affects latency, initial loading, offline support, and server capacity. The guide shows how to configure modes per page or component and choose an approach for web, desktop, or mobile applications.

Microsoft Threat Intelligence and Microsoft Security Research detail how attackers use ARTEX agents to find exposed GitHub secrets and compromise cloud resources, sometimes within five minutes. The analysis covers application credential abuse, adaptive API requests, and practical steps for credential rotation, workload identity protection, secret scanning, and threat hunting.

puneetguptams explains how to prepare an IIS virtual machine for Reader-only Azure SRE Agent investigations. The guide covers collecting request logs, Windows events, performance counters and configuration audits in Log Analytics, then adding investigation skills and alerts while keeping server changes under your team's control.

conxu-ms outlines expanded Fabric Actions and Business Actions activities in Microsoft Fabric Data Factory pipelines. The update adds more supported Fabric operations and 25 third-party connectors, with built-in connection handling and structured configuration to link data processing, semantic model refreshes, and downstream application workflows without custom API integrations.

Jesse Houwing shows how to remove unaffiliated GitHub Enterprise Cloud members using the GitHub CLI, GraphQL, and PowerShell 7. The walkthrough includes dry runs, protected accounts, batched mutations, and error handling, while explaining why organization-level SCIM does not clean up enterprise membership and where identity-provider management is required.

sbaynes describes how Microsoft uses AI to discover, remediate, and validate Windows security vulnerabilities while retaining human review. The article explains why faster update deployment matters, how security teams can use machine-readable vulnerability information, and where Windows and Azure hotpatching can help shorten exposure windows.

Karthik Raman and Brian Celenza explain how GitHub’s new Git storage architecture separates durable storage, request handling, and repository maintenance. The design combines Azure Blob Storage with a dedicated reference consensus service, supporting thousands of concurrent writers while keeping reads fast and preserving existing Git workflows.

jovanpop-msft introduces preview regular expression functions in Microsoft Fabric Data Warehouse and the SQL analytics endpoint. The update enables T-SQL queries to extract structured values from free text, validate contact formats, standardize strings, and mask sensitive values without a separate processing step.

Naomi Moneypenny introduces Moonshot AI’s Kimi K3.1 Pro in Microsoft Foundry, an open-weight model supporting text, images, and up to one million tokens of context. The announcement covers coding and research applications, token pricing, and practical evaluation criteria such as task completion, reliability, latency, and cost.

John Miller announces general availability of the Microsoft Foundry extension for Azure Developer CLI and walks through creating, testing, evaluating, and deploying hosted agents. The guide keeps agent and resource configuration alongside application code, explains remote builds, and shows how to reuse deployment and evaluation settings in CI/CD pipelines.

zoeyli introduces the private preview of managed identity authentication for Azure Container Registry Connected Registry synchronization. The article explains workload identity federation, repository-level RBAC and ABAC permissions, deployment prerequisites, and migration constraints, including one-way migration and an offline maintenance window.

Naomi Moneypenny introduces video generation models from Kling, LTX, and MiniMax rolling out in public preview through fal in Microsoft Foundry. The announcement compares model capabilities, output options, and pricing, and explains US hosting considerations for developers adding text-to-video and image-to-video capabilities to their applications.

shilmenon announces general availability of OneLake external-location support for Azure Databricks Unity Catalog on the Microsoft Fabric side. Supported managed data can reside directly in OneLake, with OneLake Security enabled by default. The article outlines setup, platform responsibilities, and the separate permissions required in Fabric and Databricks.

stevenbucher explains how Azure Policy can evaluate caller identity alongside resource configuration. The walkthrough covers blocking manual deletions, requiring stronger authentication, restricting deployment applications, and granting identity-based exemptions, followed by practical controls for rolling policies out progressively and reversing enforcement without changing policy definitions.

Mika Dumont explains how the GitHub Copilot upgrade agent helps migrate .NET applications from Windows x64 or x86 to Windows Arm64. It identifies compatibility blockers, proposes a migration plan, and updates code and project settings, while developers review changes and validate runtime behavior on matching hardware.

Ravinder Singh and Anna Hoffman discuss a Principled Technologies benchmark comparing Azure SQL Database Hyperscale with Amazon Aurora PostgreSQL I/O-Optimized. The study tests an I/O-intensive HammerDB workload across two vCore counts and multiple concurrency loads, reporting up to 52 percent higher performance and 51 percent better performance per dollar at 16 vCores.

Alym Rayani outlines Microsoft Security’s November updates, including task-scoped AI agent permissions, operating system-enforced containment, and local agent discovery. The roundup also covers SQL Server protection in Azure Government, improved visibility into Defender Experts investigations, and threat-informed initiatives for reducing security exposure.

esantana explains how to address connection pressure and read-heavy workloads in Azure Database for PostgreSQL using PgBouncer, read replicas, virtual endpoints, and Pgpool-II. The walkthrough covers installation, authentication, routing validation, and maintenance, while highlighting replica lag, middleware availability requirements, and when application-level caching with Azure Managed Redis fits.

Jan Maarten explains how GitHub now surfaces accessibility statements on repository overview pages. Maintainers can use these files to document supported environments, known barriers, contributor expectations, and reporting processes, with examples showing practical workarounds and guidance for keeping accessibility information accurate and useful.

Selim Bilgin and Silvian Goldenberg share early benchmarks for electronic design automation workloads on Azure Cobalt 200 VMs. Their analysis covers simulation, verification, and static timing performance, explains the processor and platform characteristics behind the results, and notes that the gains apply to specific internal workloads and test configurations.

Microsoft Threat Intelligence and Microsoft Defender Security Research Team analyze Q3 2026 email threats, including rising phishing volume, spoofed business-service domains, and changing attachment tactics. Their findings highlight risks from security overrides and detail two credential-theft campaigns, with Microsoft Defender mitigations, detections, and hunting queries for security teams.