#011: AI Needs Better Metaphors
Plus, my agent pays the bills, personal software goes native, and the value of being unemployed.
Imagine the scene. It’s Thanksgiving 2026 and you’re sitting next to your uncle at the dinner table. After a questionable rant about how prediction markets are the oracles of truth in the 21st century, he tells you he’s thinking about “getting into AI.” You’re relieved to finally switch the topic. He asks if you could help explain some basics. Easy-peasy, you think - you’re so AI-pilled that random numbers like 4.7 and 5.5 evoke emotional responses.
“So what’s the difference between a skill and a plugin?” he asks. “What about MCP? Is that the same as CLI? And is that the same as API?” You start sweating. “Wait, are sub-agents like agents but they’re worse than normal agents? Do CLI agents work for the CLI? What’s the difference between a routine, a scheduled task, and a cron job? Is the scheduled task not routine? What does cron mean - is that, like, the last name of the guy who invented it?” You are now questioning your life and starting to think the Polymarket sermon was actually the good part of dinner.
You think I’m joking, but please explain to me the difference between Notion’s custom agents, Claude Cowork’s scheduled tasks, and Claude Code’s routines:
At the risk of tooting my own horn, I’d say I’m as AI-pilled as they come in non-technical circles - I use AI for hours daily, I’ve built software with it, I built my own agents, skills, and plugins, I have a Hermes agent running on my Mac mini, and I have a postcard on my desk with a quote from a Claude Code session that made me laugh. And I still struggle to understand, let alone explain, the difference between all these concepts.
The problem isn’t just the confusing terminology. All these things can be understood and explained, but that’s not the point. The point is that we don’t yet have a solid set of well-fitting metaphors to ground these AI primitives. We don’t need better terminology or even better interfaces - first, we need better metaphors.
Cliff Kuang, in his book “User Friendly”1, lays out a convincing argument for why metaphors are foundational to broad technology adoption. I’m including two quotes here because they’ll do a much better job of explaining it than I will, so bear with me:
The right metaphor is like an instruction manual but better, because it teaches you how something should work without you ever having to be told. Consider the metaphor of the in-box versus the news feed. The email in-box borrows its logic from your mail, and you probably at least glance at every piece of mail that’s sent to you, simply because they were all meant for you. Your email in-box carries the same logic. The Instagram “feed” or the Twitter “stream” are entirely different metaphors. A stream rushes on even if you’re not there to see; it gurgles by in the dark, when you’re asleep. To say that information is a stream suggests that it’s there for the taking, if we wish to drink, not that we have to consume it all. A stream or a news feed, even if it’s crafted to your whims, doesn’t require your personal attention. It’s a commons to be shared.
and:
That’s how metaphors work: Once their underlying logic becomes manifest, we forget that they were ever there. No one remembers that before the steering wheel in a car, there were tillers, and that tillers made for a natural comparison when no one drove cars and far more people had piloted a boat. The metaphor disappeared once driving cars became common. In digesting new technologies, we climb a ladder of metaphors, and each rung helps us step up to the next.
Arguably, we’re already on the right path. We have collectively landed on one of the core metaphors that will underpin the next age of AI - AI as co-worker / employee. This is why the chat interface feels natural and is becoming pervasive in AI apps - we’ve been “chatting” with other humans through a computer for 4 decades. When you give something a name, a perfect command of language, and the same tools you have, it’s no different from your colleague Jerry who keeps promising to send you that brief that’s 2 weeks overdue (be honest, you can’t wait for Jerry to be replaced with AI).
The design challenge will be climbing this ladder further. The only primitives that seem to do that well currently are skills and memory - you can just understand what they are from the name and apply that mental model without problem to AI. Everything else starts getting hazy (and lazy) from here as engineers are trying to adapt terms from the previous waves of computing to describe these new concepts - cron jobs, MCPs, sub-agents, slash commands, plugins... you get the point.
Which is why everyone is trying to rename these primitives in hopes that something will click. Some think it’s a shameless rebranding. I think it’s just necessary experimentation to find the metaphor that clicks and instantly unlocks a mental model. And a good mental model is worth a thousand technical manuals. In this way, the current landscape of disparate-yet-vaguely-similar terms is just the messy middle of the necessary experimentation journey.
As we experiment, we shouldn’t forget to steal. You read that right. If a metaphor clearly works in one product, other products should adopt it. After all, Jakob’s Law still stands - people transfer their expectations between products, so they expect yours to work the same way. What I’m sure of is that these metaphors won’t all come from the prior age of technology. Like the best metaphors of the current age, the new ones will emerge from nature and human systems. And the products that will win may not be the ones with the best model or the cleanest architecture. They may be the ones that make AI primitives feel familiar enough that your uncle understands them.
3 Bits
This announcement didn’t get a ton of hype but this is a BIG deal. We’re rapidly moving towards the world where we consume and interact with the web through agents. Agent commerce is going to be the foundational piece of this future. It’s no surprise Stripe is now stepping in to fill this gap - they invested 16 years into payment infrastructure that positioned them extremely well to own this new space.
Funnily enough, I texted my friend that I wanted this exact functionality for my agent 12 hours before it got announced.
I set it up and had it pay multiple bills without a hitch in 5 minutes:
2. Glaze
The company behind Raycast recently introduced Glaze - a macOS app that lets you vibe code new macOS apps in minutes. I got to attend the early launch in NYC and take it for a spin - it’s worth the hype.
In about 10 minutes I was able to create an app to view all my AI skills in one place and another app to convert markdown files into rich HTML (I write this newsletter locally in markdown then convert it to a different format for Substack). Glaze took care of all the scaffolding, the native design system, and a slick icon (that shows up like any other app). I like this way better than spinning up obscure local web apps that I have to launch from a folder using a terminal.
There’s a part of me that feels bittersweet about this. As someone who spent years crafting macOS apps for others, the era of small well-crafted apps may be coming to an end. Or not?
I could keep lamenting forever. One thing is certain though - this is an exciting new era of personal software and I’m here for it.
Can confirm, this is a pretty neat trick.
Carveouts
I’m coming back to sketching, experimenting with screenshot-to-html workflows, and finding more fun use-cases for my Hermes agent. What are you tinkering with?
Sign-off
I want to ask you for a favor - if you’ve been enjoying the newsletter, please consider sharing it with your team / colleagues / friends. It really helps, especially in these early stages as I’m posting into the social media void and looking for like-minded people. To those who already shared - thank you, it means a lot. And yes, I’ll keep including this cringe beggar message until I hit a 1000 subscribers. Don’t @ me.
Also if you read this far and want the same postcard, reply to this email and I will ship it to you for free. See you next week.
Kuang, Cliff; Fabricant, Robert. User Friendly: How the Hidden Rules of Design Are Changing the Way We Live, Work, and Play: