Browse Artificial Intelligence Blogs (37)
Jesse Houwing clarifies GitHub Copilot’s April 24 interaction-data policy change, explaining which subscription tiers may have interactions used for training, what is and isn’t included (like private repos), and practical ways enterprises can enforce license tiers and lock down developer environments.
Emanuele Bartolesi explains how to make GitHub Copilot less “agreeable” and more useful by adding a repo-level voice instructions file that pushes Copilot to be direct, critical, and focused on correctness and maintainability.
Zure summarizes recent Microsoft Fabric and Purview capabilities for metadata management and governance, covering OneLake catalog search, workspace tagging, bulk definition APIs, and how AI agents/copilots intersect with lineage, compliance, and risk controls.
John Edward shares practical ways to control Azure-based copilot and AI agent spend, focusing on token discipline, caching, model selection, and ongoing governance so LLM solutions scale without surprise bills.
Jesse Houwing explains why he rebuilt the Azure DevOps Marketplace publishing tasks from v5 to v6, focusing on faster builds, stronger testing, GitHub Actions support, and more secure authentication (OIDC/workload identity) while using GitHub Copilot’s Coding Agent to accelerate the rewrite.
John Edward compares Microsoft Copilot Studio and Azure AI Agents (via Azure AI Foundry/Studio) to help architects choose between a low-code agent builder and a developer-driven platform based on flexibility, cost, scalability, and control.
Heidi Hämäläinen explains why Microsoft Purview Data Governance can feel heavy at first, and why governed metadata (glossary, catalog, data products, and security foundations) matters for scalable analytics, ML, and GenAI work—especially when you need discoverability, compliance, and trust in production.
Randy Pagels shares practical tips for developers to maximize GitHub Copilot's effectiveness by providing better context and intent, rather than relying on longer prompts.
DevClass.com highlights Microsoft's switch to weekly Visual Studio Code releases and the rollout of Autopilot in Copilot Chat, offering developers new AI-driven coding experiences while raising fresh security concerns.
John Edward explores the foundations of Microsoft Copilot agent design, outlining how goals, memory, tools, and autonomy create robust, autonomous AI systems for enterprise automation.
DevClass.com reports on how Microsoft Azure CTO Mark Russinovich used Anthropic’s Claude Opus 4.6 AI model to scan 1986 Apple II machine code, finding security vulnerabilities and raising important points about AI’s expanding role in legacy code security.
John Edward provides a comprehensive look at agentic AI in IT, showing how Microsoft Azure and related services create self-healing and intelligent operations through automation, monitoring, and AI-driven incident response.
DevClass.com highlights Microsoft execs Mark Russinovich and Scott Hanselman as they examine how AI coding assistants affect the role and growth of junior software developers, emphasizing new industry and educational needs.
Hidde de Smet explains practical frameworks and real-world techniques for effective prompt engineering and context engineering with LLMs and agent tools, including GitHub Copilot, helping AI practitioners move from vague queries to reliable, production-grade results.
In this workshop summary, DevClass.com reviews Martin Fowler’s event marking 25 years since the Agile Manifesto, highlighting the growing impact of AI on coding, the renewed importance of TDD, and security risks in software development.
John Edward analyzes if AI can fully replace the Solution Architect role, focusing on automation’s impact, the enduring necessity for human judgment, and specific challenges in complex enterprise environments.
Harald Binkle explores how to extend AI agents with Visuals MCP, letting tools like GitHub Copilot render interactive tables, lists, and images inside VS Code using React, TypeScript, and a flexible MCP server.
DevClass.com explores GitHub’s preview release of agentic workflows, detailing how AI agents automate repository tasks. The article, authored by DevClass.com, breaks down security, configuration, and use case scenarios for this new automation concept.
Emanuele Bartolesi shows how to use GitHub Copilot as a guardrail for generating strict Conventional Commit messages in VS Code and JetBrains Rider, with concrete instruction snippets you can paste into each IDE to make the output consistent and automation-friendly.
John Edward details how native Mermaid diagram support in Visual Studio 2026, enhanced by GitHub Copilot, empowers developers to visualize, generate, and maintain documentation seamlessly within their coding workflow.