Browse All Posts (140)

John Savill runs through the Azure Weekly Update for 4th September 2026, covering a set of platform changes across compute, AKS, networking, monitoring, security, and Azure AI Foundry, with quick pointers to what’s new and where the updates land in the Azure stack.

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.

Visual Studio Code highlights Emmet, a built-in VS Code feature that speeds up writing HTML (and related markup) using short abbreviations and expansions.

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.

Jesse Houwing shares a practical checklist for deciding whether a third-party GitHub Action is safe to run in your CI environment, focusing on maintenance signals, dependency hygiene, release integrity, and governance. He also explains why pinning what you run matters, and compares SHA pinning, immutable releases, and action lock files.

Jesse Houwing explains why GitHub Copilot cloud agent sessions can’t be spawned from GitHub Actions using GITHUB_TOKEN, and how GitHub’s accountability model (identity, billing, and auditability) shapes what “agentic workflows” can do today. He then lays out practical orchestration patterns that work, with concrete YAML examples.

Allison announces a new GitHub REST API endpoint that lets you track repository star growth over time while keeping stargazer identities private, aimed at helping maintainers and tool builders update integrations affected by earlier access restrictions.

GitHub introduces Project HydraFusion and shares benchmark results claiming higher verified task quality and lower estimated cost versus Claude Opus 5 on Terminal-Bench 2.1. The short also points developers to try HydraFusion as a selectable model via the /experimental feature in GitHub Copilot CLI.

GitHub introduces Project HydraFusion, a research preview for GitHub Copilot that orchestrates multiple AI models at runtime to balance quality, cost, and latency. The video explains how routing strategies like single, cascade, and critique workflows can automatically choose an execution path per task to improve outcomes without manual model selection.

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.

devanshirastogi rounds up five recent Azure Firewall capabilities—some now generally available and others in public preview—covering explicit proxy support, IPv6 dual-stack filtering, HTTP header insertion, auto-learned SNAT routes via Azure Route Server, and higher-throughput IDPS with TLS inspection for Azure Firewall Premium.

Jesse Houwing explains how to stop GitHub Copilot agents from confidently inventing details about fast-moving tools by grounding them in a local clone of the real repository, then forcing answers to be backed by file-and-line citations from the source.

GitHub shares a quick “The Download” roundup covering a new GitHub CLI capability for attaching images and videos to pull requests, plus several AI-related updates including local coding-agent models, large-scale LLM releases, and benchmarks and analyses focused on AI code review and PR-writing language.

rgarofalo walks through a hands-on build that locks down Azure AI Foundry both inbound (Private Endpoint) and outbound (agent egress via network injection), including the DNS zones you must create, how to prove public access is actually blocked, and how to troubleshoot opaque agent tool-call failures like 424 errors.

Andrea Griffiths talks with Angela Wen about making a first open-source contribution on GitHub, from finding a good first issue through opening a draft pull request and getting CI checks green. They also cover practical expectations when working with maintainers and what “using Copilot responsibly” looks like in a real PR workflow.

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.

James Montemagno and Matt Soucoup run a beginner-friendly livestream on the GitHub Copilot SDK for .NET, focusing on how to embed Copilot’s agent runtime into your own apps for multi-turn conversations, tool calling, streaming responses, and MCP-based extensibility.

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.

Christine Caggiano, Joshua Bradley, Steven Truitt, and William Chappell describe how Microsoft Discovery’s Discovery Engine adds CLIO (a self-adaptive “cognitive loop”) to improve agentic scientific problem-solving, and share benchmark results from Agent’s Last Exam showing higher scores and better consistency through multi-model, evidence-driven exploration.

Scirqueira shares practical operating rules for keeping a Microsoft Fabric Data Warehouse medallion architecture healthy in production, focusing on batch ingestion, rerunnable Silver transformations, consumption-ready Gold modeling, using Fabric DW defaults effectively, and monitoring performance and failures by layer.

Allison announces generally available updates to npm trusted publishing, including multiple OIDC configurations per package, staged approvals that wait for malware scanning to finish, and improved version history visibility for maintainers on npmjs.com.

Allison summarizes three GitHub Actions improvements: a new REST API to track runner version deprecation timelines, a least-privilege `vulnerability-alerts` permission for `GITHUB_TOKEN` to read Dependabot alerts, and new `job` context properties that help reusable workflows identify their source at runtime.

Fokko at Work recaps what’s new across Visual Studio Code 1.133–1.136 with a focus on GitHub Copilot features, showing practical demos like Agent Plugins support, prompt UX improvements, usage details per chat turn, and agent merge workflows.

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.

ryanjadams explains how Fabric’s “connection recency” signals help admins govern connections at enterprise scale, and how to use Fabric REST APIs plus a companion Python notebook to find stale, duplicate, and single-owner connections before taking cleanup 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.

Allison announces a required PGP signing key update for the GitHub CLI (gh) Linux APT and RPM repositories ahead of the September 5, 2026 key expiration, with guidance on who needs to update their setup and which installation methods are unaffected.

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.

wolfgangdesalvador introduces a public preview optimization for Azure Blob Storage List Blobs that returns results in Apache Arrow format, cutting response size and client parsing cost. The post explains the required REST headers and SDK versions, shows a Python decoding example, and shares rclone benchmarks demonstrating large speedups with parallel listing.

Amaury Levé explains how MSTest 4.4 uses source generation to make test projects publishable and runnable as Native AOT executables, so your tests exercise the same trimming and reflection constraints as the app you deploy.

pranabpaul walks through the first part of building a retail assistant demo using Microsoft Fabric and Azure AI Foundry, focusing on setting up the Azure environment, provisioning Fabric capacity, loading sample data into a Lakehouse, creating an ontology, and wiring a Fabric Data Agent to query that data.

pranabpaul continues the 3IQ Retail Assistant demo by wiring unstructured PDF content into an Azure AI Foundry agent using Azure Blob Storage and Azure AI Search, including the RBAC permissions needed for managed identities and the networking trade-offs involved when publishing the agent to Microsoft 365 Copilot.

Stefan Kingham’s documentary traces how Visual Studio Code evolved from early web-based editor experiments into a widely used, open-source developer tool, covering key technical and product shifts like Electron, extensions, LSP, remote development, and the editor’s adaptation to the AI era including GitHub Copilot.

GitHub explains the “AI harness” concept for guiding LLM execution, and how harness engineering adds the runtime, tools, and guardrails that let AI agents work safely against a codebase in agentic workflows.

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.

ryanjadams introduces Microsoft Fabric Connection Recency (preview) and the related REST APIs for auditing and governing connections at enterprise scale, including how to identify stale and duplicate connections and reduce ownership risk using role assignments and Entra group ownership.