All Posts

What started in Xcode 26 as a single "Intelligence" chat panel has turned, by Xcode 26.3, into a genuine three-way race: Anthropic's Claude, OpenAI's Codex, and Apple's own built-in assistant are all sitting in the same IDE, all able to touch your code, and all fighting for the same job.

The iPad has always been the creative's device — a canvas for illustrators, a drafting table for writers, a mood board for designers. Add Claude into that workflow and it becomes something more: an AI collaborator that helps you move from blank page to finished piece faster, without losing the creative edge that made you reach for an iPad in the first place. Here's how writers and designers are using Claude on iPad to sharpen their creative process.

The Mac has always been the developer's machine of choice. In 2026, it's also become the best platform for AI-assisted development — not because of any single tool, but because of how well a handful of them work together. Here's a practical breakdown of the AI stack serious Mac developers are running right now.

Token Management, Part 3 of 3.

Apple previewed the next generation of Apple Intelligence at WWDC on June 8, and unlike the 2024 rollout, most of what was shown is already in a developer beta with a public beta due in July and a full release this fall alongside macOS 27. The headline is a rebuilt Siri, but the features that will change your day-to-day are scattered across Safari, Photos, Shortcuts, and Passwords. Here's what's real, what runs on your Mac versus in the cloud, and where the caveats are. One s

Token Management, Part 2 of 3.

Getting more out of Claude · No code required

Anthropic shipped Claude Opus 4.8 this morning. If you only read the headline you’d file it under “incremental point release and move on,” and the company itself frames it that way — a modest but tangible step up from Opus 4.7, available at the same price. But a few of the things riding alongside it actually matter for how I work day to day on a Mac, and they’re worth ten minutes of your attention before you go back to whatever you were building. Here’s the short version of w

The last post walked through Power Automate cloud flows for Outlook automation from a Mac, and used Copilot in one place — to draft a flow from a natural-language description. Azure Logic Apps, which is the larger sibling of Power Automate, lets AI show up in three different places. It can write the workflow for you. It can be a step inside the workflow. And at the new edge of the platform, it can be the thing running the workflow. Each of those is a different tool with a dif

Most Power Automate tutorials quietly assume you are sitting at a Windows machine. You are not, and for the daily-email side of automation it turns out that does not matter. Cloud flows run entirely in the browser. The Outlook 365 connector talks to your mailbox over Microsoft's APIs. Copilot in the flow editor will build the first draft for you from a plain-English description. The only piece that is Mac-hostile is Power Automate Desktop, the Windows-only RPA tool — and if y

Final Cut Pro went through a long quiet stretch. For years the updates were small enough that people kept asking whether Apple had forgotten about it. Then FCP 11 shipped in late 2024 with Magnetic Mask, FCP 12 followed, and in January Apple announced the Creator Studio subscription bundle that pulls Final Cut, Logic Pro, Pixelmator Pro, Motion, Compressor, and MainStage into one package. The AI features are the part of all this that actually shows up in my edits. Here is wha

Apple announced this afternoon that Tim Cook will become executive chairman and John Ternus will take over as CEO effective September 1, 2026. Cook stays on through the summer to manage the transition, then moves to the board chair role where he'll focus on policy engagement. This wasn't a surprise. Ternus has been the favorite to succeed Cook in industry coverage for at least a year, and Apple disclosed in a filing that the board made the appointment on Friday. What's worth

If you've been following this series you already have VSCode set up with GitHub Copilot agent mode. This post puts that setup to work on something concrete: a small React app, built on a Mac, from an empty directory to a working dev server in about 15 minutes. The goal isn't to teach React from scratch — there are much better resources for that. It's to show the end-to-end workflow of building a modern React app with AI assistance sitting right next to the editor. If you've b

Apple's built-in accessibility tools on macOS Tahoe 26 are better than they've ever been. VoiceOver has been mature for over a decade. Live Captions transcribe audio system-wide. Magnifier finally came to the Mac and works with your iPhone or any USB camera. Accessibility Reader reformats any text in any app into something easier to read. If you have visual or hearing impairments and you use a Mac, the baseline is solid. What AI adds is a layer on top of that baseline — speci

Apple Intelligence on macOS Tahoe 26 is useful. Writing Tools rewrites text in place in any app. Mail summarizes threads. Image Playground generates stuff. And when Siri gets stumped, it hands off to ChatGPT (now GPT-5 as of Tahoe 26). But there's no Claude anywhere in that list, and that's a problem if Claude is the model you actually want to use. Apple is expected to fix this at WWDC 2026 in June with an "Extensions" system that lets Claude, Gemini, and other assistants plu

The series so far has been about adding MCP servers to graphical AI surfaces — Claude Desktop, Raycast, VSCode's Copilot pane. Useful, but all of them are chat windows wearing different outfits. You type something, an AI types back, tools run in the middle. Terminal-based AI is a different interaction model. You're not in a chat — you're in a shell that also happens to have an agent in it. The agent reads files, runs commands, edits code, and uses MCP servers, but the shell i

The last three posts connected the same Intune MCP server to Claude Desktop, Raycast, and VSCode. The story there was simple: one trusted API, three interaction surfaces. Low security surface area — the MCP server calls Microsoft Graph on your behalf, and Microsoft Graph does what it's told. Filesystem MCP is a different animal. The server is trivially easy to set up. The tools it exposes are useful immediately. And the security model is meaningfully more complicated, becaus

Two posts ago we set up an Intune MCP server on macOS and wired it into Claude Desktop. Last time we added Raycast so the same server was reachable from a keyboard shortcut. This post closes the loop: connecting that same server to VSCode, so fleet context is available in the Copilot Chat pane while you're writing the PowerShell, Python, or Bash script that acts on it. This is the one I reach for most when the answer isn't "tell me a number" but "help me write something that

In the last post we stood up an Intune MCP server on macOS and wired it into Claude Desktop. That covers the deep, conversational use cases — the kind where you're genuinely reasoning through a problem and want an LLM to hold the thread. But a lot of fleet work isn't that. It's the same five questions fifteen times a day: is this Mac compliant, what's its OS version, when did it last check in . Opening a chat window, waiting for the assistant to spin up, typing a full senten

If you manage a Mac fleet through Microsoft Intune, you already know the rhythm: open the admin center, wait for it to load, click through three blades, copy a device ID, paste it somewhere, cross-reference with a report, and eventually answer a question that took your colleague ten seconds to ask in Slack. The Model Context Protocol (MCP) changes that workflow. By running an Intune MCP server locally on your Mac and connecting it to Claude, you can ask things like "how many