Browse Artificial Intelligence News (425)

Natalie Guevara explains how GitHub Copilot is improving token efficiency in longer sessions by caching repeated prompt context, loading tool definitions on demand, and routing requests to the best-fit model via Auto model selection. The post also shares practical habits for reducing credit burn in day-to-day Copilot workflows.

Taesoo Kim explains how Microsoft’s MDASH agentic scanning system moved from a benchmark win into real engineering workflows, feeding validated findings into Microsoft Defender, GitHub Advanced Security, and Azure DevOps. The post breaks down recent CVEs found across Windows and identity components, plus what pipeline changes improved results and what still fails.

Rob Lefferts summarizes Microsoft’s positioning as a Leader in Forrester’s 2026 XDR Wave and explains the security platform themes Microsoft is emphasizing: cross-domain signal correlation, attack disruption, built-in threat intelligence, and SOC workflows powered by Microsoft Defender, Microsoft Sentinel, and Security Copilot.

Allison announces a new GitHub Copilot enterprise governance control that lets admins disable bypassing permission prompts (“yolo mode” / auto-approve) in Copilot clients. The update explains where to place the enterprise-managed settings file, how it’s applied to licensed users, and which VS Code versions respect the policy.

Sandeep Deo explains how AI is speeding up identity-based attacks and what Microsoft is changing across Entra and Defender to help teams prevent, detect, and respond faster. The post highlights unified identity risk scoring, improved Entra ID Protection views, least-privilege response roles, and agent-driven recommendations for Conditional Access.

amitch announces a preview ServiceNow connector that can query Microsoft OneLake data in place (zero-copy), aiming to reduce ETL and keep a single governed data foundation across Microsoft Fabric analytics and downstream operational workflows.

Jan Krivanek introduces the Microsoft Binlog MCP Server, an MCP server that lets AI assistants (including GitHub Copilot) query MSBuild .binlog files using 15 purpose-built tools for failure diagnosis, property tracing, performance bottleneck analysis, and build-to-build comparisons across Visual Studio, VS Code, and CLI workflows.

Allison announces general availability of auto model selection in GitHub Copilot Chat on github.com and the GitHub mobile app, explaining how auto routes requests to different AI models based on task complexity and real-time availability, and how it affects transparency, policy controls, and token billing.

Allison announces GitHub Copilot’s new agent finder, which discovers and ranks agent capabilities from a registry you choose, with enterprise controls over what resources can be surfaced and used.

jiang_jenny1 introduces the Fabric Spark Operations Skill (preview), an AI-assisted, read-only troubleshooting tool for Spark workloads in Microsoft Fabric. It turns common investigations—failed notebooks, pipeline failures, session triage, and performance issues—into natural-language commands that produce a severity-ranked diagnostic report with fix recommendations and links back to Fabric.

Waldek Mastykarz explains why AI coding agent extensions that perform well alone can degrade results when installed alongside other extensions, and how to measure and reduce these composition effects in real developer workspaces.

Allison announces that GitHub Copilot individual plan sign-ups are reopening (Student, Pro, Pro+, and Max) and outlines immediate changes to how upgrades and continued usage work when you approach included usage and spending limits.

Allison announces the general availability of the GitHub Copilot app for macOS, Windows, and Linux, positioning it as a desktop workflow for agent-driven development. The post highlights starting sessions from issues or pull requests, running parallel sessions per repo, reviewing diffs, and using canvases, cloud automations, and MCP-connected tools.

Ryan Caldwell and Bhavya U explain how the VS Code team is reducing GitHub Copilot’s token usage (and improving latency) in agentic sessions, with concrete changes to prompt caching, tool-definition loading, and transport choices across OpenAI and Anthropic models.

Natalie Guevara explains Git worktrees as a practical way to work on multiple branches at once without stashing or constantly switching contexts, and shows the core commands plus the trade-offs to watch for. The article also connects worktrees to parallel workflows used by tools like the GitHub Copilot app.

Allison announces that GitHub Models is being retired and is no longer available to new organizations and enterprises, while existing customers can continue using the playground, API, and models for now.

Allison announces that GitHub Code Quality moves from public preview to general availability on July 20, 2026, including new org-level rollout and reporting features plus a new pricing model that combines per-committer licensing with metered AI usage and GitHub Actions minutes for CodeQL scans.

Satya Nadella highlights an Azure milestone: a new performance record for a leading LLM training benchmark at extreme scale, achieved through full-stack work across silicon, systems, networking, and software in partnership with NVIDIA.

Waldek Mastykarz explains why AI coding agents often keep using deprecated tooling (like legacy CLIs) even after teams ship replacements, and outlines practical ways to measure and correct agent behavior using extensions, explicit deprecation signals, and better naming.

Chris Welsch reports on İmeceMobil, an agriculture platform built on Microsoft Azure that helps Turkish farmers use AI-driven satellite imagery analysis, hyperlocal weather alerts, and expert guidance to improve crop decisions. The piece also highlights the Azure services and security tooling used to run the app at scale.

diptiborkar announces new Microsoft Fabric and Azure Databricks interoperability that lets teams use Microsoft OneLake as a shared, native storage layer, including GA read access and beta support for writing Unity Catalog managed tables. The post also frames OneLake as a governed data and context foundation for analytics and AI agent workloads.

Allison explains an update to GitHub Copilot enterprise usage reporting: usage metrics now combine server-side telemetry with client-side IDE signals, so more active (billed) users appear in single-day and 28-day reports, even when client telemetry doesn’t reach GitHub.

Natalie Guevara introduces the most useful slash commands in GitHub Copilot CLI, showing how to control the terminal agent by switching models, checking token/context usage, resuming sessions, reviewing diffs, changing directories, and resetting tool permissions.

Jeff Pinkston summarizes a year of real-world email security benchmarking data comparing Microsoft Defender with SEG and ICES vendors, highlighting where layered defenses help most and where Defender’s detection and remediation have improved over four quarters.

Dylan Birtolo explains a Copilot CLI rollout that makes subagent delegation more selective, reducing unnecessary handoffs and improving reliability and wait times. The post breaks down the delegation failure modes they observed, the orchestration policy changes they shipped, and how they validated the impact with offline tests and production A/B experiments.

Allison announces new controls for GitHub Copilot code review, including organization-level runner configuration (GitHub-hosted, self-hosted, or large runners), support for Copilot content exclusions at repo/org/enterprise scope, and removal of the 4,000-character limit for repository custom instruction files.

Natalie Guevara summarizes GitHub’s May 2026 availability incidents and the reliability work underway, including moving parts of the monolith to Azure, isolating database domains, and hardening GitHub Actions and Copilot services against cascading failures.

MichalBar introduces a preview redesign of Microsoft Fabric Real-Time Dashboards tile editing, adding Copilot-assisted visual authoring alongside a more code-friendly KQL workflow. The post walks through creating a visual from a prompt or query, iterating with history, and testing parameterized queries directly in the editor.

Allison explains an update to GitHub AI usage reports so GitHub AI Credits usage is reflected in the standard report fields, including what to use going forward and what changed for data since June 1.

Waldek Mastykarz explains how AI coding agents can silently scaffold outdated Node.js projects when they run npx without pinning versions, due to npm’s engine-aware manifest selection. The post breaks down why this happens and gives practical steps to make agent-driven scaffolding more predictable.

Allison announces a new /settings command in GitHub Copilot CLI that centralizes configuration into a schema-driven interface, supporting an interactive full-screen dialog, inline one-liners, and reset-to-default workflows with tab-completed keys and validation.

Allison announces the public preview of GitHub Agentic Workflows, a GitHub Actions capability that lets teams define reasoning-based automations in natural-language Markdown and compile them into standard Actions YAML, with built-in controls aimed at keeping agent-driven changes safe to apply.

Natalie Guevara explains how GitHub improved secret scanning alert quality by adding LLM-based contextual verification, reducing false positives while keeping detection coverage. The post breaks down where verification fits in the pipeline, what “better context” means in practice, and the measured impact on customer-confirmed false positive alerts.

Allison announces that GitHub Agentic Workflows can now authenticate using GitHub Actions’ built-in GITHUB_TOKEN instead of a personal access token, reducing the risk of long-lived credentials and enabling organization-level billing for Copilot CLI usage in agentic workflows.

Laura Jiang announces Copilot Autofix in limited private preview for GitHub Advanced Security for Azure DevOps, which generates suggested fixes for supported CodeQL alerts and turns them into pull requests. The post explains what’s covered in preview, how the workflow fits into existing review gates, and how usage is billed via Azure.

Leah Tran introduces Visual Studio 18.7’s pull request review experience, which lets developers open PRs, browse diffs, discuss comments, and approve or merge changes from inside the IDE for both GitHub and Azure DevOps repos.

Allison announces an update to GitHub Copilot Chat on the web that improves handoff to Copilot cloud agent sessions and adds ways to query previous sessions. The release surfaces in-progress agent status in chat, enables pulling agent logs into the conversation, and adds session search for summarizing past work.

Waldek Mastykarz explains how to measure whether an AI coding agent extension actually improves generated code, using controlled comparisons, clear evaluation criteria, and repeatable scenario runs while tracking both quality and token cost.

Waldek Mastykarz explains why piling up dozens of agent “skills” can quietly burn your token budget and reduce response quality, and how to decide what should stay a skill versus what should become a manually-invoked prompt in tools like GitHub Copilot and VS Code.

Jeffrey Fritz announces the .NET Day on Agentic Modernization livestream (June 16, 2026), focused on practical ways to modernize existing .NET applications without a full rewrite. The agenda highlights GitHub Copilot-assisted modernization, Aspire-based approaches, migration of WinForms and line-of-business apps, and adding agentic/AI capabilities.