Browse All Posts (1506)

dotnet covers the production-readiness pieces for an AI agent, focusing on observability with OpenTelemetry, governance and data protection with Microsoft Purview, and quality evaluation as the SDK evolves, then shows how to deploy the agent to Foundry Hosted Agents and maintain it with a refresh-prompt workflow.

dotnet demonstrates how to make an AI agent interact with real user data more safely by adding file access, explicit human approvals for sensitive actions, and durable memory that persists across restarts.

dotnet explains four additions that make an AI agent more practically useful: skills for loading domain knowledge on demand (including centrally managed skills in Azure AI Foundry), constrained shell access for file work, a CodeAct sandbox for writing and running code, and background agents for parallel research.

dotnet demonstrates how to stand up an agent “harness” in C# using a single AsHarnessAgent call, then incrementally add tool calling, web search, and planning so a vague request becomes a tracked, step-by-step execution loop.

Microsoft Developer demonstrates building the “Sparkles” AI agent in VS Code using the Microsoft Foundry Toolkit, including deploying a model, wiring up an MCP server, and validating the agent with traces and evaluation runs for repeatable testing.

Visual Studio Code shows how to use the Command Palette to navigate faster in VS Code, including opening recent files, jumping to symbols in the current file, grouping symbols by type, and searching for symbols across the entire workspace.

Microsoft Security Research, Sagar Patil, Arlette Umuhire Sangwa, Jesse Birch and Ravikant Tiwari break down a hands-on-keyboard intrusion that starts with Microsoft Teams helpdesk impersonation, escalates through remote-control sessions and a malicious MSI, and ends with Node.js-based persistence and WinRM lateral movement, with concrete mitigations and Defender XDR hunting queries.

Cassidy Williams breaks down the new AI vocabulary showing up in developer conversations—loops, harnesses, squads, hill climbing, and model “openness”—and explains how these concepts map to practical ways teams build and improve agent-driven workflows (with GitHub Copilot as a concrete example of a “harness”).

ryanjadams explains how to keep Fabric Data Factory pipelines and Copy Jobs fully private when moving data to or from Snowflake, using Workspace-level Private Link, a private Azure Storage staging account, and Snowflake’s Azure Private Link storage integration.

Allison announces an update to GitHub Copilot enterprise-managed settings that lets organizations set any Copilot model as the default for new conversations, with optional per-team overrides via managed settings files.

Allison announces general availability of content exclusion support in the GitHub Copilot app and Copilot CLI, so enterprise, organization, and repository admins can prevent Copilot from using specified files as context and better protect sensitive code during agentic workflows.

Erik Kristensen explains how GitHub Copilot reduced end-to-end cost for agentic coding by optimizing whole tasks (not individual tool calls), including selective compression of noisy command output, removing wasted formatting, tightening prompts with regression tests, and batching background results to avoid extra model turns.

John Maeda shares a practical take on what’s genuinely new in AI: setting a clear goal, defining how you measure progress toward it, and using iterative loops that “hill climb” toward better results as tokens get cheaper and more capable.

GitHub’s podcast episode with Cassidy, Marlene, and GPS breaks down emerging AI terms—loop engineering, harness engineering, and squads—and connects them to practical agentic workflows, including how iteration loops affect cost and performance and how “open weight” differs from truly open source AI.

The Visual Studio Code Team shares Insiders updates for VS Code 1.137, focusing on Copilot-related workflow improvements such as clearer model token limits, better context handling when pasting GitHub issue/PR links, and updated new-session composer controls.

Mads Kristensen shows how to give each Visual Studio solution its own color theme so multiple IDE instances are easier to tell apart. He also explains the new scoped settings model in Visual Studio 2026, where solution-level settings are stored in a JSON file you can optionally commit to source control for consistent team setup.

James Montemagno introduces VS Code agent plugins and how they package and share AI customizations—like skills, MCP servers, and custom agents—so teams can reuse the same setup across projects and environments.

AmirJafari announces general availability of the Microsoft Fabric data agent integration in Copilot Studio, enabling agents to call governed Fabric data as a tool (Fabric IQ Data MCP) and return permission-respecting, data-grounded answers. The post highlights the new tool-based authoring experience, improved orchestration, and expanded publishing targets.

GitHub hosts a multi-hour Copilot Day live session covering new releases, hands-on demos, and practical workflows, including how Copilot works across GitHub, the CLI, and VS Code, plus a live-coding segment with Burke Holland, Pierce Boggan, and guests.

John Savill gives a quick, practical explanation of why generative AI models sometimes “hallucinate” (confidently produce incorrect information) and why this behavior is a natural outcome of how models generate text from probabilities rather than retrieving verified facts.

wolfgangdesalvador breaks down Azure’s MLPerf Storage v3.0 results for Azure Managed Lustre, focusing on how sustained throughput and fast checkpoint I/O help keep large AI training clusters from stalling.

Alex-wdy explains an upcoming Azure Key Vault control plane API retirement and the required tooling upgrades to avoid breaking vault management operations. The post lists minimum Azure CLI and Az PowerShell versions, how to check what you have installed, and the exact upgrade commands to run before the February 27, 2027 deadline.

Sithu explains why long-running Azure Batch tasks on Ubuntu nodes can get interrupted and re-queued on a daily schedule, even when the app itself never fails. The post shows how to confirm the cause on a node and how to stop the restarts without breaking your pool operations.

gurjsing shows how to turn Microsoft’s published compliance scope (using Germany’s C5 as the example) into enforceable Azure controls by extracting the certified-service list from the Service Trust Portal, mapping it to ARM resource types, and deploying a deny/audit Azure Policy with a reviewable, automated workflow.

Microsoft Security Research, Microsoft Defender Experts and Parth Jomadkar document a malware campaign that uses look-alike software download sites and regenerated installer archives to compromise Windows systems. The post breaks down the attack chain, provides Defender XDR detections and KQL hunting queries, and lists practical mitigations and IOCs defenders can apply.

Amit Ganguli announces the public preview of the Resiliency Agent in Azure Copilot, which helps teams assess zonal resiliency across subscriptions, prioritize fixes with cost-aware indicators, and generate deployment-ready Bicep/Terraform templates and scripts to remediate gaps.

Microsoft Developer demonstrates how to turn a deployed model into a reusable AI agent using the Microsoft Foundry SDK in Python, including adding instructions, running a multi-turn conversation, and wiring in MCP tools so the agent can take actions while maintaining context.

Allison announces general availability of Enterprise Live Migrations (ELM), a GitHub Enterprise feature for near-zero-downtime migrations from GitHub Enterprise Server to GitHub Enterprise Cloud with Data Residency, including cutover behavior, monorepo support, and CLI-based lifecycle management.

GitHub introduces a GitHub CLI update that lets developers attach local images or videos to issues, pull requests, and comments using a repeatable --attach flag, making it easier to share visual context directly in GitHub discussions.

Allison announces a generally available GitHub billing update that lets admins set an expiration date on individual user budgets, so temporary budget overrides are removed automatically and users fall back to the next applicable budget.

Sreekanth Thirthala introduces APIOps CLI, an open-source command-line tool for managing Azure API Management configuration as source-controlled artifacts, enabling reviewable pull-request workflows and repeatable promotions across environments using GitHub Actions or Azure DevOps pipelines.

Michaela Isaacs explains the GA transition in Power BI and Microsoft Fabric from embedded ODBC drivers to Apache Arrow Database Connectivity (ADBC) drivers, why it improves large-result performance and security posture, and how to validate the change ahead of the tenant-wide cutover.

Allison announces a public preview update to GitHub Copilot code review that adds approval assessments on pull requests and, when enabled by admins, allows Copilot to submit an approval that can count toward required-approvals rules.

Microsoft Developer presents a student-focused course that uses the GitHub Copilot app to turn a resume into a live portfolio site, while teaching Git fundamentals, GitHub Pages deployment, Copilot modes, context/tokens, MCP servers, skills, and bring-your-own-model with Azure AI Foundry.

bgautam announces general availability of the Microsoft Fabric Admin API for listing workspace networking communication policies tenant-wide, aimed at improving security auditing, compliance monitoring, and governance reporting across Fabric workspaces.

Microsoft Defender Experts Cybersecurity Incident Response describes Microsoft DART’s Cybersecurity Incident Response Readiness Workshop, a scenario-driven engagement that stress-tests incident response plans with realistic attack simulations, threat hunting exercises, and feedback on how people, process, and telemetry hold up under pressure.

Nimrod Shalit introduces a new set of Microsoft Learn resources for implementing CI/CD in Microsoft Fabric, covering platform concepts, best practices, and hands-on tutorials for deploying Fabric items across dev/test/prod using Git integration, Azure DevOps pipelines, Terraform, the Fabric CLI, and the fabric-cicd library.

GitHub runs a beginner-friendly virtual training on the GitHub Copilot SDK, focusing on how developers can programmatically interact with Copilot and build custom agent capabilities that fit their team’s workflows across multiple languages.

Jonah Andersson explains how to take AI agents from prototype to production by building MCP servers on Azure Functions, using .NET to expose tools that agents can discover and invoke at runtime. The session uses a DevOps CI/CD scenario where agents detect deployment issues, diagnose failures, and create rollback PRs in Azure DevOps.

Allison announces an update to GitHub Discussions that lets owners of personal repositories block or unblock users directly from a discussion comment, matching the in-context controls already available for issue and pull request comments.