Stephen Millard’s Stream Deck Plugin

I’ve been using Stream Deck for years, and like many of you, I’ve cobbled together various plugins to make it work with my Mac automation setup. KMLink for Keyboard Maestro and separate plugins for shortcuts. It was messy. My friend Stephen Millard fixed all of that… This is a post for MacSparky Labs Pathfinder and Insider Members only. Care to join? Or perhaps do you need to sign in?

Apple’s Big Hardware Week

Apple kicked things off today with the iPhone 17e and a refreshed iPad Air powered by M4. Both look like solid updates. The iPhone 17e brings the A19 chip and doubles the base storage to 256GB while keeping the same $599 starting price. The iPad Air gets the M4 with more memory and a faster Neural Engine. Pre-orders for both start Wednesday.

But the announcement I’m most excited about is the new budget MacBook, expected later this week. A low-cost Mac laptop could open the platform to a whole new group of users. People who’ve been priced out of the Mac or stuck on Chromebooks will finally have an on-ramp. That’s good for them and good for the platform. I’ll have more to say once Apple makes it official.

Nobody Can Make Fun of Phone Cameras Anymore

I was sitting in the dark of my backyard last night, admiring the planets, as you do, when I noticed a blob of something in the tree looking down at me. My distance vision is 20/20, yet I still could not make it out. I pulled out my iPhone and used the 5x lens in dark mode. It kept the shutter open for a few seconds and returned this image.

February in the MacSparky Labs

MacSparky Labs members get to participate in member events and receive a number of exclusive videos and podcasts each month. Here’s a summary of offerings this past month:

February 2026

  • 2026-02-27 – February in the MacSparky Labs (M,I,P) (Post)
  • 2026-02-27 – The Lab Report for February 27, 2026 (M,I,P) (Podcast)
  • 2026-02-26 – Book Club: Intentional (Event) (M,I,P) (Event)
  • 2026-02-26 – Exploring iPhone Capture Techniques (M,I,P) (Video)
  • 2026-02-24 – Do Everything on Your Mac with the Keyboard, Easily (I,P) (Video)
  • 2026-02-20 – The Lab Report for February 20, 2026 (M,I,P) (Podcast)
  • 2026-02-19 – Deep Dive – Home Screen Lab (Feb 2026) (P) (Video)
  • 2026-02-17 – DEVONthink AI-Assisted Naming and Filing (M,I,P) (Video)
  • 2026-02-15 – The Keyboard Tomb (M,I,P) (Post)
  • 2026-02-14 – Labs February Meetup Summary (I,P) (Post)
  • 2026-02-13 – Supercharge Updates (M,I,P) (Video)
  • 2026-02-13 – Lab Report 2026-02-13 (M,I,P) (Podcast)
  • 2026-02-12 – February Deep Dive – Building Useful Home Screens (Event) (P)
  • 2026-02-10 – Deep Dive – Using Claude Cowork (Media Release) (P) (Video)
  • 2026-02-06 – My OpenClaw Experience (Video) (M,I,P)
  • 2026-02-06 – Lab Report 2026-02-06 (M,I,P) (Podcast)
  • 2026-02-05 – Fixing Text with Keyboard Maestro (I,P) (Video)
  • 2026-02-03 – Introducing Stephen Robles (M,I,P)

Labs content and its membership level: P – Pathfinder; I – Insider; M – Member

If you’d like to be a part of the MacSparky Labs, you can get more information and join right here.

The Feedback Loop Between Teaching and Learning

I’ve been thinking a lot lately about teaching.

I’ve taught the Productivity Field Guide workshop three times now. Each year it gets better. Not because I’m a better teacher, though hopefully I am.

The workshop gets better because my students make it better.

The act of teaching it live sparks magic. Participants ask questions I didn’t anticipate. People get stuck on concepts I thought were obvious. They have breakthroughs on exercises I almost cut from the program. Every single one of these moments changes the content (and me).

This year we spent a lot of time on role statement exercises. I’ve used role statements for years, but watching a room full of smart people work through them, watching the moment it clicks, watching them rewrite their own statements forced me to think deeper about why this actually works.

Teaching forces clarity. When I’m writing alone, I can let things slide. I can tell myself the idea is there, even if the explanation is fuzzy.

But in a workshop, there’s nowhere to hide. If my explanation doesn’t land, I see it immediately. So I try a different angle. I find a better example. I cut the stuff that doesn’t matter and expand the stuff that does.

The questions also help me. Someone asks why a particular workflow matters. I try to answer but I can see it didn’t really land. I have to dig deeper, articulate what I actually mean. Often, my answer ends up better than anything I would’ve written at a desk.

The struggles matter too. When someone can’t make a technique work in their own life, that’s information. It tells me where the gap is between theory and practice.

This is why I’ll keep teaching workshops even though it’s more work. The content gets better. My understanding gets better. And the people in the room get something more useful than they would if I’d just written a book and mailed it to them.

Teaching forces you to question your thinking and assumptions. If you want to get better at something, teach it.

Drafts Just Got a Lot Smarter (Sponsor)

This post is sponsored by Drafts. Sponsorship doesn’t influence what I write. Here’s my take.

I’ve been a Drafts user since its release. It’s the first place text goes on every device I own. Grocery lists, blog post ideas, meeting notes, quick reminders. Anything that starts as words starts in Drafts.

What makes it work is speed. You open the app and start typing. No picking a folder. No choosing a notebook. Just a blinking cursor ready to go. You sort it out later, and Drafts gives you the tools to send that text wherever it needs to end up.

Version 50 Is a Big Deal

Greg Pierce just shipped Drafts v50, and this one matters for anyone who cares about automation.

The Shortcuts support got a complete overhaul. There are now over 50 Shortcuts actions.

You can query drafts by date ranges and location, access version histories, control the interface, and run granular commands for appending, prepending, and editing drafts. The kind of stuff that used to take workarounds now just works.

On the Mac side, the AppleScript integration got a serious expansion. You can query your entire draft library, update drafts, run actions, and work with workspaces. If you’ve ever wanted to build Mac workflows that pull from or push to your Drafts library, this is the update you’ve been waiting for.

The MCP Server for Claude

This is the one that caught my attention. Greg built an MCP server that connects Drafts directly to Claude. If you use Claude Desktop or Claude Code on your Mac, you can now talk to your Drafts library through the AI.

That means you can ask Claude things like “summarize the drafts I created this week” or “find all my drafts tagged with project-x.” You can create new drafts, run actions, and manage your library through natural conversation. It connects through AppleScript locally on your Mac, so your data stays on your machine.

I set this up and it took about two minutes. You can install it right from Claude Desktop’s Extensions settings. Search for “drafts” and it’s there. For anyone already using both Drafts and Claude, this is worth trying immediately.

There are plenty of note apps. What keeps me in Drafts is the philosophy behind it. Text first. Decide later. The capture friction is zero, and the automation layer lets you build exactly the workflows you need.

With v50, that automation layer got considerably deeper. Whether you’re building Shortcuts on your iPhone, writing AppleScript on your Mac, or connecting to AI through MCP, Drafts meets you where you work.

Check out Drafts if you haven’t already. And if you’re already a user, make sure you’re running v50.

AI Agents Need Guardrails

We are roaring into useful, agentic AI. I’ve been saying for a while now that we’re heading into it faster than the security models can keep up. So I wasn’t surprised to see Tailscale announce Aperture, a governance layer for AI agents.

The trouble with AI agents is that they run afoul of the overriding security principle of the last 30 years, which is to prevent access whenever possible. In order to be useful, an AI agent needs access. The security model has to adapt.

Aperture sits between your AI tools and the services they connect to. It routes requests through a gateway tied to user identity. Instead of distributing API keys to every agent and user, you keep one key per provider on the gateway. Aperture tracks who initiated each action and what the agent actually did. If something goes wrong, you have a trail.

It also gives security teams the ability to see and stop tool calls before they execute. That’s the piece that matters most. You’re not just logging what happened after the fact. You’re able to intervene.

I recorded a YouTube video recently about my experience with OpenClaw, a fully autonomous AI setup. I turned it on. Then I turned it off. The security exposure was too much. Aperture is exactly the kind of infrastructure that needs to exist before autonomous agents become practical for real work.

Tailscale isn’t alone here. Expect a lot of companies making announcements like this in the coming months. The AI capabilities are racing ahead. The governance and security layers are playing catch-up.

The AI tools are getting powerful fast. The guardrails need to keep pace.