Browse All Artificial Intelligence Content (841)

Allison announces general availability of assisted permissions in GitHub Copilot CLI, GitHub Copilot app, and Visual Studio Code. A language model evaluates command, file-path, and URL requests, automatically allowing those classified as clearly safe. Enterprise administrators can control available permission modes and set defaults for new sessions.

Alper explains how Microsoft Fabric’s preview React visualization libraries support analytics apps built with AI coding agents. Using Vega-Lite specifications and shared data, theming, and interaction contracts, the components provide reusable charts and grids with formatting, scrolling, tooltips, and consistent styling rather than requiring each app to recreate these behaviors.

Louis Erbkamm shares how Arnis converts real-world geographic coordinates into playable Minecraft worlds using OpenStreetMap data. The video explores the project's international contributor community and how its sole maintainer uses GitHub Copilot to triage bug reports, review pull requests, and keep the project moving.

Allison announces GPT-6.1 Terra’s general availability in GitHub Copilot for everyday agentic coding and terminal tasks. The model uses provider list pricing under usage-based billing, with gradual rollout across supported clients. Business and Enterprise administrators can control access through model policies and default enablement settings.

sbaynes describes how Microsoft combines AI agents, testing, static analysis, and formal verification to transform large codebases. The article covers Windows toolchain migration, C/C++ modernization into Rust, and specification-driven validation, explaining how small expert teams review shared knowledge and system properties rather than every generated change.

sbaynes describes using the Microsoft Discovery app to adapt insect-monitoring systems for the Asian citrus psyllid, a pest that spreads citrus greening disease. The case study covers grounded AI agents, experimental design, permitting, and synthetic biometric data for preliminary edge classifiers, with scientists reviewing decisions throughout the workflow.

Rena Liu introduces Azure AI Speech LLM 09-2026, adding 25 languages and faster multilingual transcription. The announcement covers recognition improvements, locale selection, phrase lists, and REST API configuration, with automatic service-side deployment requiring no customer action.

Cynthia Zanoni and Pooja Yarabothu explain how Microsoft’s PostgreSQL extension brings database exploration, SQL editing, and troubleshooting into VS Code. They show how GitHub Copilot can help interpret schemas and query plans, while emphasizing result verification and careful review of performance recommendations before making changes.

Visual Studio Code demonstrates how the PostgreSQL extension and GitHub Copilot help you explore an unfamiliar database. The episode covers inspecting schemas, tables, views, and functions, visualizing relationships, asking context-aware questions in Copilot Chat, and checking answers against the database to understand its data model.

Visual Studio Code demonstrates a PostgreSQL workflow combining the PostgreSQL extension’s IntelliSense and database context with GitHub Copilot. The video covers drafting, explaining, analyzing, and improving SQL queries, then running them, inspecting results, and exporting data without leaving the editor, while keeping developers in control of the final queries.

John Savill examines why AI agents fail beyond the model itself, covering unclear goals, bad context, tool misfires, reasoning errors and lost state. He also discusses hijacking, excessive privileges, limited visibility and an improvement loop for understanding and addressing failures.

Welcome to this week's AI roundup, covering Azure Local's sovereign AI announcements, the LiteLLM supply chain compromise, and Microsoft's controls for agent identity and permissions. Foundry's browser automation tool reaches general availability, while upcoming Foundry workflow and Fabric integration retirements give teams migration deadlines to plan around. We also examine agent development, retrieval, and evaluation examples, alongside research that pairs AI assistance with human oversight and explicit verification, distinguishing available capabilities from previews and planned releases.

Microsoft Developer highlights three updates: .NET 11 is ready for serious production validation, Python 3.15 defaults to a native Arm64 runtime on Windows on ARM, and browser automation in Microsoft Foundry is generally available. The video outlines what these changes mean for developers.

Microsoft Developer demonstrates how to protect an AI agent from malicious user input and instructions hidden in tool responses. The walkthrough configures Microsoft Foundry guardrails and Prompt Shields, replays both attacks, and uses traces to show where protections intervene before the agent acts.

Ben Steenhoek and Ulugbek Abdullaev explain how configurable eagerness lets paid GitHub Copilot subscribers adjust inline suggestions in VS Code. They describe the low, medium, and high modes, the training approach behind them, reward-hacking mitigations, and experimental results showing how suggestion frequency and size change.

John Savill reviews this week's Azure and AI updates, including networking, backup, monitoring, storage, and identity changes. Topics include Traffic Manager integration with Azure DNS, keyless TLS, Cosmos DB key rotation, Azure Databricks private networking, and Copilot Studio agent identity.

Allison announces an update to the GitHub Copilot usage metrics API that adds a new totals_by_client breakdown, letting enterprises and organizations see request, session, and token usage coming from tools outside the IDE (like OpenCode, Copilot CLI, VS Code, and JetBrains).

Visual Studio Code introduces a four-part video series focused on doing more PostgreSQL work directly inside VS Code, including connecting to databases, writing and optimizing SQL, using GitHub Copilot to understand database context, and troubleshooting performance, with Azure mentioned as the underlying platform for modern PostgreSQL workloads.

Allison announces an updated GitHub app for Microsoft Teams that combines GitHub notifications with GitHub Copilot-powered actions, letting teams respond to issue and pull request updates by mentioning @GitHub to investigate, fix bugs, run tests, and open pull requests from within Teams.

Microsoft Cloud outlines a “Physical AI” vision for industrial scenarios, describing how AI systems can perceive, reason, and act in the physical world across manufacturing, quality, and supply chains, and how organizations can move from simulation to real operations spanning edge and cloud.

Microsoft Security Research, Mahesh Mandava, Srinivasan Govindarajan, Sagar Patil and Suriyaraj Natarajan break down the LiteLLM 1.107.0 supply-chain compromise, showing how Python startup hooks enabled credential theft without importing LiteLLM, what data was targeted, and how to investigate and recover using Microsoft Defender detections and hunting queries.

GitHub demonstrates a hands-on workflow for going from a GitHub issue prompt to a deployed AI agent inside the GitHub Copilot app, using Azure AI Foundry tooling to provision resources, deploy a model, validate grounding to reduce hallucinations, and ship a secure proxy plus a website chat widget.

sbaynes introduces Microsoft research on evaluating step-by-step clinical diagnostic reasoning with SDBench and the Microsoft AI Diagnostic Orchestrator (MAI-DxO), including accuracy and cost results across NEJM and MIMIC-IV-ED cases and plans to open-source parts of the benchmark for reproducible evaluation.

Microsoft Developer introduces the idea of “adaptive” software that can reason and take actions, positioning it as a shift beyond apps that only respond to user input.

Allison summarizes the September 2026 update for GitHub Copilot in Visual Studio 2026, including PR exploration via the Git agent, preview BYOM support (with a breaking change to the new Agent harness), and a new flow to fix NuGet Audit vulnerabilities directly from the Error List.

Allison announces an update to the Copilot usage metrics API that reports configured names for custom skills, custom agents, MCP servers, slash commands, and plugins (instead of grouping them as “other/custom”), making it easier for admins to track adoption and usage trends across an organization.

isaiahhoyer describes using Microsoft Discovery agents to adapt Microsoft Premonition biological monitoring systems for citrus pests. The case study covers grounding agents in engineering documents, designing field experiments, preparing permit requests, and generating synthetic wingbeat data for preliminary edge classifiers, with scientific review and human oversight throughout.

sbaynes introduces Flint-interactive, a language that helps AI agents generate interactive data visualizations (not just static charts) using high-level semantic events and update operators, so users can click, filter, zoom, and link interactions across charts, text, tables, and app state.

Allison announces general availability of a global default policy for GitHub Copilot features on Copilot Business and Copilot Enterprise, explaining how unconfigured settings will be enforced during the rollout and where admins can review and override defaults.

Christoph Berlin explains how an AI agent can speed up root cause analysis by correlating data and reducing the dependency on tracking down subject-matter experts, helping engineers start investigations with better initial context.

MinseokSong explains how production failures shaped translation review in Co-op Translator. Rather than relying on quality scores or model verdicts alone, the project checks document structure, preserves human edits where possible, and records unresolved failures. The approach gives reviewers concrete checks while leaving meaning, terminology, and readability to human review.

MichalBar introduces a preview feature in Microsoft Fabric Real-Time Dashboards that uses Copilot to generate purpose-built custom visuals. By describing an operational question in natural language, dashboard authors can have Copilot create both the KQL query and an HTML-based visualization directly as a new dashboard tile.

Allison announces a new “Industry comparison” view in the GitHub Copilot impact dashboard, letting opted-in enterprises benchmark agentic adoption and leverage against aggregated peer data, with controls for policy-based participation, daily refresh, and data residency boundaries.

Microsoft Developer walks through how developers (and AI coding agents) can build applications with Azure SQL, including a demo flow that starts from an Azure SQL DB container and moves into Azure SQL Database’s free tier, plus an overview of Microsoft SQL agent skills and plugin concepts.

Marko Hotti and Patty Chow show how to build an Azure Cosmos DB app using AI-assisted development, starting from a blank folder and a product spec to generate a working travel planner. They cover data modeling, container design, queries, and local testing using the Cosmos DB Linux emulator and GitHub Copilot in VS Code.

GitHub explains how GitHub Copilot approvals can help teams avoid routine pull request review bottlenecks by letting Copilot provide delegated review approvals that count toward merge protection rules, while still combining that automated assessment with a human approval to satisfy branch requirements.

Marko Hotti and Madeline Egan explain how to move an AI agent from a demo to a production-ready system using Azure Cosmos DB, focusing on observability and evaluation practices like tracing, regression testing, and before/after metrics to improve retrieval quality, latency, token usage, memory efficiency, and RU consumption.

Marko Hotti and Madeline Egan show how to build AI agents that keep durable, shared memory across sessions using Azure Cosmos DB, so a multi-agent travel planner can remember user preferences, share context between agents, and continue work after handoffs instead of restarting from scratch.

Marko Hotti and Patty Chow demonstrate how to build a smarter AI travel planner on Azure Cosmos DB by combining operational app data with vector embeddings and search features, so the app can answer nuanced queries while still respecting real inventory and booking workflows.

Microsoft Developer shows how to use Agent Optimizer in Azure AI Foundry to improve an agent when prompt tweaks aren’t reliably fixing behavior. The video walks through building an evaluation dataset, scoring a baseline, generating candidate instruction sets, and validating improvements (quality, latency, and safety) before shipping a new agent version.