Storybook's official MCP server (@storybook/addon-mcp) turns your component library into a live knowledge source for AI agents. Agents can query component documentation, generate stories, run interaction and accessibility tests, and self-correct — all without you having to intervene. This guide covers the architecture, the three toolsets, installation step-by-step, and two alternative MCP approaches including the community-built storybook-mcp package.
Blog
Microsoft Scout: The Complete Guide to Microsoft’s First Always-On Autopilot Agent
Microsoft Scout is Microsoft's first Autopilot agent, announced at Build 2026. It's a desktop AI application for Windows and macOS that acts on your files, shell, browser, and Microsoft 365 data — with its own Entra identity, heartbeat background mode, automations, and sub-agent delegation. This guide covers everything: what it is, what it can do, how access works, enterprise governance, and what it means for Power Platform and enterprise developers.
Work IQ APIs: Microsoft’s New Intelligence Layer for Enterprise Agents Is Now Generally Available
Work IQ is Microsoft's new intelligence layer for Microsoft 365, announced at Build 2026 and going generally available June 16, 2026. It gives agents — and the developers building them — a way to work with business context rather than raw data: 2x faster than traditional APIs, 80% fewer tokens, 10 MCP tools instead of hundreds, and full M365 tenant security. This post covers the architecture, the five core advantages, how to get started with the MCP server and CLI today, and what it means for Power Platform developers building on Dataverse and M365.
Microsoft’s AI Found 16 Windows CVEs — Including 4 Critical RCEs. Here’s How the Agentic Pipeline Actually Works
Microsoft's MDASH agentic scanning harness found 16 CVEs in the Windows networking stack — including 4 Critical RCEs affecting tcpip.sys, IKEv2, DNS, and Netlogon. As a Power Platform Solution Architect, this is the infrastructure your solutions sit on. This post explains how the pipeline works, what the architectural lessons are, and how to use this in client governance and security conversations.
Claude Fable 5 in GitHub Copilot — Technical Breakdown for Power Platform and Enterprise Teams
Claude Fable 5 is Anthropic's first Mythos-class model and it's now generally available in GitHub Copilot. This breakdown covers the technical specs, the built-in Opus 4.8 fallback mechanism, the 30-day data retention requirement that breaks standard ZDR assumptions, and a practical enablement framework for Power Platform and enterprise teams operating under data governance constraints.
GitHub Copilot Code Reviews Are Coming to Azure Repos — What It Means for Power Platform Teams
GitHub Copilot code review is entering limited public preview inside Azure Repos pull requests. This guide covers three-tier setup, billing on your Azure subscription, preview limits, and how to integrate AI-assisted code review into Power Platform ALM workflows for Dataverse plugins and PCF controls.
Dataverse MCP Server: The 15 Tools That Make Power Platform Agent-Ready
Microsoft formalized the Dataverse MCP server tool shape in June 2026 — 15 named tools that give any MCP-compatible agent grounded, auditable access to your Power Platform environment. This analysis covers the full tool surface organized by risk tier, how to configure clients in VS Code and Copilot Studio, the billing model, and a dedicated security and governance breakdown: Entra ID auth, RBAC, client allowlisting, audit gaps, prompt injection risks, and the delete-override danger in the sample agent instructions.
Think Before You Build: GitHub Copilot’s Plan Agent in Visual Studio — Structured AI-Assisted Development
GitHub Copilot's Plan agent, introduced in Visual Studio in May 2026, adds a deliberate planning phase before any code generation happens. Instead of watching AI modify files in unpredictable directions, you review and approve a detailed Markdown plan grounded in your actual codebase — before a single file changes. This guide covers how the Plan agent works step by step, how to write prompts that produce genuinely useful plans, and how to apply it to a real Dataverse plugin refactoring scenario with working before-and-after code examples.
JavaScript vs TypeScript Web Resources in Model-Driven Apps: Complete Guide
Plain JavaScript is quick to ship. TypeScript bundled with Webpack or esbuild is built to scale. This article walks through both approaches end-to-end so you can make an informed choice for your next project.
Speaking at Nordic Summit 2026: Microsoft Copilot Studio vs Azure AI Foundry
My session Microsoft Copilot Studio vs Azure AI Foundry has been accepted for Nordic Summit 2026 — the largest Power Platform and Dynamics 365 conference in the Nordics. Taking place 21–22 September 2026 at LEGOLAND® Hotel & Conference in Billund, Denmark, the session gives solution architects and Power Platform developers a practical decision framework and hybrid architecture playbook for choosing between the two platforms.
Entire.io for Power Platform Developers: Why AI Coding Sessions Need a System of Record
AI coding agents like Claude Code and GitHub Copilot generate Power Platform solutions at speed — but when the session ends, the reasoning behind every plugin stage, Client API pattern, and architecture decision disappears from the git history. Entire.io is a CLI-first system of record that captures those AI coding sessions as permanent, searchable records linked directly to your commits. This article explains why Power Platform developers need this more than most and how Entire fits into the full code-first development stack alongside microsoft/power-platform-skills and microsoft/Dataverse-skills.
Dataverse Actions, Functions & Flows in Power Apps Code Apps: Complete Guide
I've been building Power Apps Code Apps for a while now, and the question that kept coming up was always the same: how do I call actual server-side logic from here? With the @microsoft/power-apps npm CLI hitting v1.1.1, that question finally has a clean answer. This guide walks through everything — discovering and scaffolding Dataverse actions, functions, and Power Automate flows, the generated TypeScript service classes, error handling, deployment, and the architectural decisions I'd make on a real project.