Browse All Artificial Intelligence Content (890)

mosiddi explains how the Agent Governance Toolkit (AGT) tackles post-hoc accountability for autonomous agents: proving who authorized an action, what scope was delegated across multi-agent chains, and whether audit evidence was tampered with, using cryptographic identities, signed delegation links, and append-only audit logs.

Natalie Guevara summarizes GitHub’s April 2026 availability incidents, including outages and degradations affecting code search, audit logs, Copilot services, Pages, Codespaces, Actions, and other platform features, with root causes and concrete follow-up actions to improve detection, resilience, and recovery.

Patty Chow explains what it takes to move an AI agent beyond a demo, focusing on “memory” as an architecture decision that affects cost, recall quality, and user experience, and demonstrating an MCP server running inside GitHub Copilot backed by Azure Cosmos DB.

Imran Siddique and Shawn Henry explain how Microsoft Agent Framework and the Agent Governance Toolkit (AGT) fit together to run AI agents safely in production, with deterministic runtime policy checks, budget enforcement, and end-to-end auditability across local and cross-boundary (A2A) agent interactions.

Allison announces a technical preview of the GitHub Copilot app, a GitHub-native desktop experience for running focused, isolated agentic coding sessions from issues and pull requests, then validating changes and landing them through normal PR review and checks.

Ayan Gupta shows how to take GitHub Copilot’s Java modernization workflow out of the IDE and run it at scale from the terminal, producing assessment reports, upgrade plans, diffs, and pull requests across many repositories, and wiring the process into repeatable CI/CD and scheduled jobs.

Alyssa Ofstein and Elliot H Omiya explain how defense in depth needs to adapt for autonomous AI agents, focusing on application-layer controls that bound what agents can do, how they get permissions, when humans must approve actions, and how identity makes agent behavior auditable.

Jim Harrer announces the VSLive! Microsoft AI Hackathon 2026 at Microsoft HQ in Redmond, a hands-on evening build event designed to help teams ship real prototypes using Azure OpenAI, Azure AI Foundry, GitHub Copilot, and agent-based patterns, with judging criteria that emphasize architecture, security, and practical value.

stclarke summarizes SAP Sapphire 2026 announcements focused on running SAP workloads on Azure and moving enterprise AI from pilots to production, including Azure OpenAI + Copilot Studio scenarios, Microsoft Fabric connectivity to SAP data, sovereign cloud options for regulated industries, and Sentinel-based monitoring for SAP landscapes.

Microsoft Defender Security Research Team and Yossi Weizman break down real-world “exploitable misconfigurations” in cloud-native AI apps—especially Kubernetes deployments where exposed services and weak auth can lead to RCE, credential theft, and data leaks—and show what to harden and what Defender for Cloud can detect.

Allison announces that GitHub Copilot’s cloud agent now supports Auto model selection, letting Copilot pick the best available model based on system health and performance, with a discounted model multiplier and no weekly rate-limit impact.

The Visual Studio Code Team shares the 1.121 (Insiders) release notes, covering Copilot Chat and agent terminal improvements, model picker updates, terminal output compression for common dev tools, SSH authentication enhancements, and a newer bundled ConPTY on Windows.

SurenderSinghMalik breaks down recent Azure App Service (Linux) changes that make Python deployments faster and more reliable for AI-heavy workloads, including new compression and packaging defaults, fewer expensive file operations, and client-side improvements that reduce transient deployment failures.

GitHub hosts a “Rubber Duck Thursdays” chat session covering open source topics, GitHub Copilot discussion, and general developer coworking and news.

EfratNauerman announces a public preview update for the Azure Copilot Observability Agent in Azure Monitor, focused on using chat-driven investigations and exploration to speed up triage and root-cause analysis across logs, metrics, traces, and alerts in distributed systems.

vikas_gautam describes an end-to-end architecture for bringing Databricks Genie into Microsoft Teams using an Azure AI Foundry agent, focusing on what breaks in private, regulated environments and how to handle networking isolation, multi-hop identity, and per-user authorization when querying governed data.

Authorised Territory demonstrates a .NET data ingestion pipeline that converts a PDF to Markdown via the MarkItDown MCP server, generates embeddings with a local Ollama model, and stores those embeddings in SQL Server 2025 running in Docker Desktop.

Allison announces updates to GitHub Copilot for JetBrains IDEs, including a public preview of the Copilot CLI agent inside the IDE, a unified sessions view for tracking agent runs, and new agent-mode capabilities like an Ask question tool and global custom agent configuration.

Jacob Wilkinson introduces the Power Apps MCP Server and Agent Feed (public preview) and shows how Copilot Studio agents can surface tasks, blockers, and proposed data changes inside model-driven apps so business users can supervise autonomous work without breaking the agent’s flow.

Rob Bos introduces the GitHub Copilot App technical preview and shares a practical first look at using it for repository maintenance, including parallel agent sessions, session modes (Interactive/Plan/Autopilot), and the Agent Merge workflow for handling CI failures, merge conflicts, and security-related alerts.

Michael Flanakin summarizes FinOps toolkit 14, including a Copilot Studio agent template for querying FinOps hub data with KQL, a new recommendations pipeline that ingests Azure Advisor and Resource Graph results, a simplified hub deployment UI, and a preview dataset for commitment discount eligibility.

Rob gives a first look at the new GitHub Copilot desktop app, showing how it shifts Copilot work into a project-based, chat-first workflow. He demonstrates starting sessions from issues and PRs, running multiple concurrent worktrees, and letting Copilot plan, implement, and open pull requests with checks and merge handling.

Bruno Capuano and Jose Luis Latorre preview what to watch for at Microsoft Build 2026 around .NET and AI, including agentic patterns, copilots, and expected updates across the Microsoft developer ecosystem.

Brigit Murtaugh introduces the VS Code Agents window (Preview), a dedicated VS Code window designed for an agent-first workflow where chat and session tracking are the main interface for coordinating higher-level tasks across projects.

Mark Russinovich explains why debugging generative AI systems differs from traditional software debugging, focusing on probabilistic behavior, agentic decision chains, and why outcomes can vary from run to run.

RavinderGupta outlines a “self-healing” CI/CD pattern where an agent observes Azure DevOps pipeline failures, uses Azure OpenAI (via Microsoft AI Foundry) to analyze build logs, and then proposes or applies fixes—such as updating Terraform for Azure Internal Load Balancer configuration—by opening a pull request for review.

Shreyas Canchi Radhakrishna announces a preview update to Microsoft Fabric Data Agent that expands how it can query Eventhouse KQL databases by understanding user-defined functions, materialized views, and shortcut tables, improving consistency, performance, and access to external data sources.

Allison announces a public preview REST API that lets Copilot Business and Copilot Enterprise customers start and track Copilot cloud agent tasks programmatically, enabling custom automations that fan out work across repos and open pull requests with validated changes.

Amir Jafari announces preview support for service principal (SPN) authentication for Microsoft Fabric data agents, explaining why app identities matter for production deployments and outlining two common patterns: calling a data agent directly from a custom app, or routing through a Microsoft Foundry agent.

Simona Liao introduces Agent Skills in Visual Studio, a way to package reusable, task-specific instructions so Copilot agents can follow your team’s workflows and standards. The post shows how to create and manage skills in the IDE or from your repo, and when to use skills versus custom instructions.

Ayan Gupta demonstrates how the GitHub Copilot app modernization extension containerizes a Java 21 application with Docker, validates it locally, and then provisions Azure infrastructure and deploys to Azure Container Apps using built-in tasks and an agent-driven workflow.

John Edward explains how GitHub Copilot changes team workflows around pull requests, code review expectations, and knowledge sharing. The article focuses on the trade-offs of faster AI-assisted coding, why review discipline matters more, and how teams can add guardrails like testing and security scanning without losing collaboration.

Microsoft Developer explains practical ALM patterns for taking Copilot Studio agents from experimentation to production, focusing on repeatable deployments, environment isolation, and governance-friendly configuration using solutions, environment variables, and connection references.

Microsoft Developer presents a session on building agentic user interfaces across Copilot and the Power Platform, with demos that connect Copilot and Power Apps and a look at newly released MCP app UI capabilities for creating custom, purpose-built interfaces.

Microsoft Developer kicks off the Agent Academy Hackathon, explaining how to participate and what kinds of AI agents you can build with Copilot Studio, along with links to the Agent Academy learning path and hackathon registration.

Microsoft Developer explains why AI agents that look good in demos can fail in production, and outlines a practical approach to testing agents built with Microsoft Copilot Studio—covering prompts, grounding, actions, and orchestration under real user behavior.

Microsoft Developer walks through building employee experience AI agents with Microsoft Copilot Studio, showing how to connect knowledge grounding with real workflows using MCP-based integrations and Power Platform automation across several practical workplace scenarios.

syedarshad walks through a practical workflow for testing AI agents with LangSmith, using Azure OpenAI as the target model. The guide shows how to build an evaluation dataset, run LLM-as-judge scoring (correctness and hallucination checks), and interpret per-example and aggregate results with tracing and experiment views.

Leon Welicki explains how Power Platform is positioning existing Power Apps (canvas, model-driven, and code apps) for “agentic” workflows, including how agents integrate into apps, how Microsoft 365 Copilot can surface app fragments via MCP, and how developer tools like GitHub Copilot plug into the same managed platform.

Microsoft Developer introduces agent flows in Microsoft Copilot Studio, focusing on how to build agentic automations that stay reliable for business-critical processes by combining deterministic, structured steps with AI-driven judgment where it’s needed.