MailMaven: The Email Client for Mac Power Users (Sponsor)

My thanks to SmallCubed for sponsoring MacSparky this week.

When Apple pulled the rug out from under third-party Mail plugins, a lot of power users lost tools they depended on. SmallCubed’s MailSuite (MailTags, Mail Act-On) was one of the big ones. Rather than walk away, the SmallCubed team did something ambitious. They built their own email client from scratch.

MailMaven is that client, and it’s built specifically for Mac users who want more control over their email without handing their messages to someone else’s servers. Your mail stays on your provider and your computer. Nothing gets routed through a third party. If you care about privacy, MailMaven also supports end-to-end encryption via PGP.

The feature set reads like a wish list for anyone who’s ever outgrown Apple Mail. There’s a powerful tagging system that goes well beyond labels. You can attach dates, notes, and colors to messages. The rules engine is extensive, giving you fine-grained control over how incoming and outgoing messages get sorted. Smart mailboxes and fast search make it easy to find anything in your archive.

If you’re coming from Apple Mail, migration is seamless. And if you want to go deep, Joe Kissell wrote two books on the app, “Get To Know MailMaven” and “Take Control of MailMaven,” both included free with your purchase.

A couple of things worth noting on the roadmap: version 1.1 is coming at the end of the month and will add POP support. AppleScript support is in the works for version 1.2 later this year. MailMaven will also be featured on ScreencastsOnline in upcoming episodes.

MailMaven is a one-time purchase that includes the first year of updates and data syncing. You can keep using the app indefinitely, and extended maintenance plans are available if you want continued feature updates down the road. No subscription required.

MacSparky readers can get 20% off their purchase with coupon code MACSPARKY2026 at checkout. That includes the first year of updates and data syncing. The offer runs through the end of March.

Check out MailMaven →

Mac Power Users 841: Robot Assistant Field Guide

This week on Mac Power Users, Stephen and I go deep on the robot assistant system I’ve been building with Claude Cowork. We cover the whole journey — from why chatbots never quite delivered on their productivity promises to the combination of skill files, MCPs, and managed agents that finally made AI genuinely useful for the donkey work of running a creative business. I walk through practical examples including automated file renaming, email processing, sponsor invoicing, and podcast post-production pipelines. Stephen also shares his new Studio Display XDR setup and we dig into Perplexity Computer as another emerging option. Fair warning: I also confess to switching back to Gmail, so prepare your hot takes.

Episode Links

This episode of Mac Power Users is sponsored by:

  • SaneBox: Take back control of your inbox.
  • Ecamm: Powerful live streaming platform for Mac.

The Case for an Ultralight Mac

The MacBook Neo is here, and it’s already obvious it will be a massive hit for Apple. People are going to buy so many of these. It will be transformative and bring lots of new users into the Apple ecosystem.

But I want to talk about what the Neo isn’t. If you’ve been waiting for Apple to make a truly ultralight Mac, something more premium, smaller, and yes, more expensive, the Neo isn’t that machine. The Neo is about accessibility and volume. It’s the MacBook for everyone.

I want the other thing.

Apple has made ultralight laptops before. The original MacBook Air was a revelation when Steve Jobs pulled it out of a manila envelope in 2008.

But every ultralight Mac has been held back by the same problem: Intel. Those chips ran hot, throttled under load, and demanded compromises in battery life that made the “Air” name feel like a warning label as much as a product category.

That constraint is gone now. Apple silicon changed everything about what’s possible in a thin enclosure.

The M-series chips run cool, sip power, and deliver performance that would have seemed absurd in an ultralight just five years ago. The engineering that makes the current MacBooks Air and Neo possible is the same engineering that could make something even more ambitious.

Think about it. Apple has covered the pro market with the MacBook Pro lineup. The Neo is about to cover the mainstream and budget-conscious buyer.

But there’s a gap at the top. A premium ultralight for people who travel constantly, who want the absolute minimum weight and footprint, and who are willing to pay for it. A MacBook that weighs two pounds or less, with a stunning display and all-day battery life. Not a compromise machine. A showcase.

The technology is ready. Apple silicon was basically designed for this. The question is whether Apple sees the market opportunity, or whether they think the Air (or whatever it becomes post-Neo) already fills that slot.

I don’t think it does. There’s a difference between a laptop that happens to be light and a laptop that’s built from the ground up to be as light as physically possible. Apple used to understand that distinction. The original Air proved it.

With the Neo handling the mainstream, there’s room in the lineup for Apple to go back to that idea. Not an Air. Not a Pro. Something else entirely. Something that shows what Apple silicon can really do when weight is the primary design constraint.

I’d buy one tomorrow.

Pixelmator Pro FTW

I recently realized that I’ve stopped using every photo editing app except Pixelmator Pro. It happened gradually over a couple of years, but now it’s the only tool I reach for.

I love Acorn and respect the other developers making great image editors. But Pixelmator Pro has become so ingrained in my workflow that I don’t even think about alternatives anymore. Whatever I need to do with an image, I know exactly how to do it in Pixelmator Pro.

Sometimes the best app isn’t the one with the most features. It’s the one you know so well that it disappears. Pixelmator Pro has become invisible to me in the best possible way.

The Robot Assistant Field Guide is Here

I spent the better part of a year experimenting with AI and coming away unimpressed.

The chatbots were fine for generating a quick summary or answering a trivia question. But every time I tried to use them for real work, the same problem showed up. They had no memory. No connection to my actual files. No way to do anything except talk. I’d describe a task, get a wall of text back, and then do all the work myself anyway.

Then Claude Code arrived. Suddenly the AI could read and write files on my computer. That changed things. I could point it at a folder full of notes and say “find every open task and organize them by project.” It would actually do it. But Claude Code ran in the terminal, which meant I had to think like a programmer to get anything done.

When Claude Cowork showed up, the programming barrier disappeared. Same power, but now I could just talk to it. Describe what I needed in plain English and watch it work. That’s when things got interesting.

Add MCPs (connectors that let the AI talk to your calendar, email, Slack, and other apps) and the whole picture comes together. Memory, because it reads your files. Skills, because you can teach it how you work. Reach, because it connects to the tools you already use. That’s the formula.

Once I had all three pieces, I started building. Email processing first. Then daily planning. Then task management. Then customer support, content publication, journaling, sponsor tracking, podcast production, weekly reviews, and a shutdown routine that wraps up my day in fifteen minutes instead of an hour.

At some point I looked up and realized I’d built something. Not a chatbot I ask questions. A system. A persistent assistant that knows my projects, remembers what I told it three weeks ago about that contractor invoice, and handles the tedious stuff I used to spend hours on every day.

I call it my robot assistant.

The biggest difference isn’t even the time saved. It’s that I stay in the zone. I used to break focus a dozen times a day to deal with admin. Email, invoicing, task shuffling, calendar juggling. Every interruption costs more than the minutes it takes. It costs the momentum. The robot handles the donkey work now, and I keep working on the stuff that actually matters.

Today I’m releasing the Robot Assistant Field Guide. It teaches the method behind everything I just described. How to use Claude Cowork and Obsidian to build your own personal AI assistant from scratch.

I want to be clear about what this is and what it isn’t. This is not “let AI write your stuff.” If you want a tool that does your thinking for you, this isn’t it. The Robot Assistant Field Guide teaches you to build an assistant for the donkey work. The email triage, the task management, the scheduling, the data entry, the repetitive admin. So you have more time for your real work.

You get ten foundation videos, about three hours total, that take you from zero to a working robot assistant. Each video builds on the last. By the end you have a functioning system ready for real work.

Then the 10-week live workshop series starts April 2. These aren’t webinars. They’re hands-on working sessions where we build real workflows together. Email processing. Calendar and daily planning. Task management. Personal CRM. Review cadences. All recorded if you can’t make it live.

You also get a Starter Kit with a vault template, sample workflows, and an AI-powered assembler that personalizes everything to your work. You don’t need to be a programmer. You need a Mac and a willingness to try something new.

The price is $199, one-time purchase, no subscription. Use code ROBOTLAUNCH for 10% off through March 30.

Get the Robot Assistant Field Guide

I’ve made a lot of Field Guides over the years. This one feels different. It’s the first time I’ve taught you to build the actual tool. The robot assistant isn’t a demo. It’s how I work now. And I think it can be how you work too.

Here’s the first Foundation Video: