Browse Artificial Intelligence News (386)

Allison announces new generally available GitHub Copilot usage metrics that track activity in the dedicated VS Code Agents window, including both aggregate (enterprise/org) and per-user fields for 1-day and 28-day reporting periods.

Allison announces improvements to GitHub Copilot code review, including automatic resolution of addressed review comments, smarter commit message suggestions when applying Copilot fixes, and deeper review analysis using Copilot SDK shell tools plus an ensemble approach for Lite reviews.

Tomoko Tanaka shows how her team turned event marketing runbooks into “ops as code” using GitHub Issues, GitHub Actions, and GitHub Copilot. The post breaks down the repo patterns (issue forms, labels, skills in Markdown, and a DRY_RUN switch) that automate setup, daily screening, and post-event reporting with guardrails.

Allison summarizes the September 7 weekly GitHub Copilot releases, including Jira integration in the Copilot app, Project HydraFusion model orchestration in Copilot CLI, new agent automations and voice mode updates in VS Code, and expanded enterprise sandbox controls for Copilot in JetBrains.

Kayla Cinnamon explains how to review agent-generated changes inside the GitHub Copilot app using three built-in panels: a diff view for inspecting edits, a terminal for running project commands, and a browser preview for validating UI changes before creating a pull request.

Brendan Burns explains why Microsoft was named a Leader in the 2026 Gartner Magic Quadrant for Container Management, and uses the announcement to outline how AKS, Azure Container Apps, Azure Arc, and Fleet Manager are positioned for AI, hybrid, and edge container operations at scale.

Allison announces a public preview that adds GitHub REST API endpoints for enabling and managing GitHub code scanning’s AI Scan for pull requests at both the organization and repository level, making it easier to roll out AI-powered security detections across selected repos without manual UI configuration.

yaronc announces a preview Fabric REST API that exposes item lineage as a dependency graph you can query from code, enabling automated impact analysis, documentation/catalog scenarios, CI/CD checks, and richer context for AI agents that need to reason about upstream sources and downstream consumers.

Rena Liu announces Azure AI Speech LLM 2607 and explains what changes for developers building speech-to-text and real-time voice experiences, including better multilingual and mixed-language recognition, improved punctuation and numeric transcription, lower latency, and a simpler phrase list parameter for domain-specific customization.

Microsoft Security Research breaks down a large-scale business email compromise campaign that used AI-assisted executive impersonation and fake invoices to push finance teams into fraudulent ACH payments, and maps practical mitigations using Microsoft Defender for Office 365, Defender XDR, and Security Copilot.

Steve Sweetman explains how to govern AI agent spend in Microsoft Foundry by combining request-path token limits, observability (traces, monitoring, evaluations), and finance-grade budgets, then tying those signals to ROI so teams can decide what to optimize, scale, or retire.

Allison announces the deprecation of the MAI-Code-1-Flash model across GitHub Copilot experiences and points Copilot Enterprise admins to the steps needed to enable the replacement model via Copilot model policies and settings.

Juan Montes profiles Kinaxis’ Maestro platform and how it uses Azure (including AKS, Databricks, Azure OpenAI, Cosmos DB, and Azure AI Content Safety) to run large-scale supply chain scenario modeling, forecasting, and agentic AI experiences. The piece also touches on Kinaxis’ internal use of GitHub Copilot for an agentic, PR-driven development workflow.

Jakub Oleksy’s August 2026 GitHub availability report breaks down five production incidents across GitHub Actions, authentication, and Copilot services, including what failed, how GitHub mitigated impact, and what reliability work is planned next (capacity, autoscaling, retries, and regional failover).

Nick Brady rounds up July and August 2026 updates for Microsoft Foundry, including GA for Hosted Agents, Voice Live integration, and Toolboxes, plus Model Router pool/region changes and new model releases. It also calls out SDK migrations (Python/JS/Java/.NET) and runtime requirement bumps you should test before upgrading.

Allison announces generally available enterprise managed permissions for GitHub Copilot agent operations, letting admins centrally decide which actions are blocked, require human approval, or run without prompting across supported Copilot clients.

The Visual Studio Code Team shares the VS Code 1.138 Insiders changelog, focusing on Agent Host and Agents window improvements like shareable session links, side-by-side agent sessions, repo-first context attachment for issues/PRs, voice mode session awareness, and agent-session cleanup controls.

Allison announces agentic autofix for GitHub Code Quality, letting teams select up to 25 findings and assign them to GitHub Copilot in one action. Copilot applies fixes on a branch, validates the changes, and opens a pull request for review, with usage governed by existing enterprise policy and AI credits.

Waldek Mastykarz explains how to pick a “minimal viable model” for AI coding work by running your own evals instead of defaulting to the most expensive option. Using GitHub Copilot Chat in VS Code, he compares model quality scores and per-run costs across real upgrade scenarios to show why “smarter” can be worse value.

Allison announces updates to GitHub Copilot for JetBrains, including enterprise-managed sandbox policies, cross-file cursor jumps for next edit suggestions, global project context in chat, and enterprise policy diagnostics. The release also adds a preview integration that connects Copilot CLI terminal sessions to IDE context and improves reliability across MCP and agent sessions.

Allison announces GitHub Enterprise Server (GHES) 3.22 general availability, highlighting updates for enterprise administration and collaboration, including Copilot CLI support for disconnected environments, enterprise teams, improvements to repository rulesets and required reviewers, and UI enhancements for issues and pull requests.

sbaynes announces codename MDASH, Microsoft’s multi-model agentic code-scanning system now deployed in Azure Government, aimed at finding and validating exploitable vulnerabilities across software supply chains with fewer false positives and more actionable results for security teams.

Aseem Datar explains how Microsoft Discovery applies agentic AI to scientific and engineering R&D, focusing on adaptive reasoning loops that explore multiple hypotheses, preserve evidence, and decide when to change strategy or involve domain experts. The post also highlights benchmark results for Discovery Engine with CLIO across several scientific domains.

Justin Yoo walks through a practical profiling workflow for distributed .NET apps, showing how to identify which process owns a slow user interaction, use Visual Studio CPU profiling to rule out CPU-bound work, and then measure hidden async waiting that doesn’t show up in CPU samples.

Allison’s weekly Copilot changelog highlights new model options (Claude Fable 5.1 and Gemini 3.8 Flash), stronger content protection via honored content exclusions in Copilot app/CLI, and VS Code 1.136 updates aimed at managing agent sessions and getting pull requests ready to merge.

Shayak Lahiri explains why Edge AI shifts security responsibility into customer-owned infrastructure, and outlines practical patterns for protecting model weights, credentials, and data. The post focuses on gating sensitive asset release using runtime attestation and artifact provenance, plus deterministic mediation to constrain what models can do.

Allison announces general availability of OpenAI’s GPT-6 Astra in GitHub Copilot, highlighting its strength on long-horizon, agentic coding tasks, how it’s billed under usage-based pricing, and where developers and admins can enable and select the model across supported IDEs and clients.

Justin Bettencourt’s August 2026 Azure SDK roundup highlights new and updated client libraries across .NET, Java, JavaScript/TypeScript, Python, Go, and more, including Document Translation 2.0.0, Azure Storage Blobs 12.30.0-beta.1, and the first stable release of Azure AI Discovery.

sbaynes shares a short update on HydraFusion in GitHub Copilot, highlighting a shift from picking a single model to orchestrating multiple models that plan, build, critique, and complete coding tasks, with a claim of up to 67% lower cost for comparable outcomes.

GitHub Staff introduces Project HydraFusion, a GitHub Copilot research preview that orchestrates multiple LLMs at runtime to balance quality, cost, and latency for coding tasks. The post explains HydraFusion’s execution patterns, operating principles for safe repo-level changes, and benchmark results across TerminalBench, DeepSWE, and an internal Copilot session benchmark.

Wes Steyn and Eduard van Valkenburg announce a preview integration that adds durable, cross-session memory to Microsoft Agent Framework agents using Azure Cosmos DB. They explain how the Cosmos-backed context provider participates in the agent lifecycle, and show a Python example that stores conversation turns, extracts memories in the background, and recalls them in later sessions.

sbaynes announces GPT-6 Astra rolling out via the Microsoft Foundry Limited Access Program, focusing on agentic, multi-step work (planning, tool use, and computer use across apps) and the enterprise controls needed to run it safely in production, including identity, networking, governance, and monitoring.

Andre Terceros and Bodhisatva Gautam announce a preview of Workspace Outbound Access Protection (OAP) in Microsoft Fabric for Operations Agent and Fabric Maps, explaining how workspace admins can enforce a default-deny model for outbound connections, allow only approved endpoints, and get clearer visibility into blocked actions.

Allison announces the deprecation of several AI models used across GitHub Copilot experiences on October 2, 2026, and outlines the replacement models plus the admin steps needed to enable them via Copilot model policies.

Jeremy Winter argues that getting enterprise AI into production is less about picking a single model and more about running an end-to-end system on Azure—spanning infrastructure, data, governance, security, and operations. The post highlights Microsoft AI Foundry, Fabric, Purview, and Azure databases, plus modernization workflows that include GitHub Copilot.

Allison announces that Gemini 3.8 Flash is now available as a selectable model in GitHub Copilot, including where it can be used (IDEs, CLI, and cloud agent), who gets access across Copilot plans, and how admins can control enablement via model policy.

Steve Sweetman and Naomi Moneypenny announce general availability of OpenAI’s GPT-6 Astra in Microsoft Foundry, focusing on agentic, cross-application “computer use” and enterprise readiness. The post highlights deployment options (Standard vs Provisioned Throughput), Global vs US Data Zone availability, token-based pricing, and the security/governance controls used to run these workflows in production.

sbaynes introduces MAI-Transcribe-2, a speech-to-text model positioned for low-latency, multilingual transcription with features like diarization, word-level timestamps, keyword biasing, and configurable output styles, alongside benchmark results and launch pricing aimed at high-throughput transcription workloads.

Kayla Cinnamon explains how the GitHub Copilot app can run multiple agent sessions in parallel on the same project by isolating each session with its own Git worktree, so you can queue up tasks (like feature work, accessibility review, and tests) and review results as they complete.

Microsoft Security Research (Noam Kochavi and Sarah Wolstencroft) explains how “ASCII smuggling” with invisible Unicode tag characters moved from AI prompt-injection research into real-world phishing evasion, and shares practical detection and mitigation guidance for email defense pipelines.