NEW TO RAMH?

Welcome. You’ve found a curious little corner of the internet for people looking for richer ways to think, create and work with AI.

You probably arrived through a post, a recommendation, or one of the robots wandering loose on the internet. Either way, I’ll show you around.

ROBOTS ATE MY HOMEWORK is a publication for thoughtful, curious people who want to do more with AI than produce things faster.

I’m Mia, a writer and AI Narrative Architect. I tend to start with a question about the mind, a creative problem, a piece of culture, or something odd the robots are doing, then follow it through research, experiments, books, film, language, art, history, and whatever else changes the question along the way. The rabbit hole is allowed. It just has to bring something useful back.

Around here, AI gets more interesting jobs than writing things for us. It might challenge an argument, help you learn a difficult subject, inspect an archive, rehearse a decision, surface a forgotten connection, or become part of a strange little system built for one specific problem. The point is to find out what becomes possible when AI makes the human more capable too.

RAMH is where I follow those questions in public. Some discoveries become essays. Some become experiments. Some become methods or robots inside RobotsOS. Plenty remain questions for longer than is convenient.

Every week, I follow a question far enough to find out what it changes, whether that means a better way of seeing something, a useful experiment, a method worth keeping, or occasionally nothing useful at all (also allowed).

  • Free posts (every Wednesday): complete essays, cultural investigations, arguments, experiments, and occasional practical methods designed to change what you notice, understand, question, or want to try.
  • Paid posts (two Fridays a month): deeper investigations, original methods, experiments, and builds you can bring into your own work. Paid members also get the complete RobotsOS library and Robots MCP.

If you need a map, these are the five territories I return to most often:

🧠

Critical Thinking & AI

How we think, question, learn, research and interpret with AI around.

Takeaway

A sharper question, stronger judgment, or a better way to figure out what you actually think.

🤖

AI Systems & Your World

Interesting ways to make AI more useful to the way you actually work, from unusual how-tos and specialist robots to context, archives and personal setups.

Takeaway

A better use of AI, or a setup you can adapt to something of your own.

👁

Taste, Voice & Originality

How we learn what good looks like, develop stronger standards, form preferences, and make choices that give work character.

Takeaway

A better eye for what belongs, what doesn’t, and why.

✨

Exploring Creativity with AI

How AI can expand creative range, help us make stranger connections, experiment more freely, and attempt things we might not have tried otherwise.

Takeaway

A new connection, experiment, or thing you suddenly want to make.

🎭

AI, Narrative & Meaning

How stories, language, framing, interpretation and context shape what something means when AI joins the process.

Takeaway

A better understanding of how meaning is made, carried, changed, or occasionally misunderstood by a robot.

The free newsletter isn’t a trailer for the paid one. I don’t hand you the problem on Wednesday and hide the useful part behind Friday’s paywall. Every free piece is complete. Paid RAMH is where selected questions go further and become methods, experiments and systems you can actually use.

Do I need to know much about AI?

Not really. RAMH isn’t a beginner AI classroom, but you also don’t need to understand APIs, build agents from scratch, or spend your evenings comparing model benchmarks.

If you’ve opened ChatGPT, Claude, Gemini, or another AI and had a conversation, you’re ready to read RAMH. To use RobotsOS, you need to be comfortable uploading a file, answering questions, and bringing a real piece of work into the chat. The robots handle the methodology. You keep the judgment.

Completely new? Open whichever AI you already have, ask it to help with one real problem, and talk back when it gets something wrong. That’s enough to begin.

A tiny note on the terminology: RobotsOS contains different kinds of systems. Some are skills, some are agents, some are playbooks or larger working setups. Around here, I usually call all of them robots, because life is short and product taxonomy isn’t why you came.

🤖 Not sure which robot you need?

Good. You shouldn’t have to memorise the whole library.

Tell the RobotsOS Advisor what you’re working on, what’s stuck, or what has gone suspiciously beige. It can point you toward the right specialist, or a combination that makes sense for the job.

What is RobotsOS?

RobotsOS is the applied side of RAMH: a growing library of specialist AI collaborators and methods for thinking, researching, deciding and making better with AI.

Some robots help you develop an idea, research past the obvious, pressure-test your thinking, inspect a draft, appraise an archive, learn something difficult, or work out why a piece of work feels wrong even when it looks technically fine.

Others help AI understand more of what matters to you, so it can work with your accumulated context, references and standards instead of treating every conversation like the first day on the job.

You can download the robots, adapt them, argue with them, or use compatible ones through Robots MCP inside the AI you already have. The MCP works more like a studio than a shelf of individual tools: bring it a problem, and it can call on several specialist robots together when the job needs more than one kind of thinking.

The library keeps growing as new questions and experiments survive long enough to deserve a robot of their own.

Inside the living library

You’ll find specialist collaborators, practical methods, context systems, experiments and larger working setups built from real RAMH questions. Each one exists because there was a job worth doing better, not because another AI workflow seemed like a nice thing to collect.

And inside Paid RAMH

Paid editions stand on their own as deeper investigations, participatory experiments, methods and builds that take selected ideas further.

Paid RAMH, RobotsOS and Robots MCP all belong to the same membership. The essays investigate the questions. RobotsOS gives useful methods a form you can reuse. The MCP brings the specialists into your existing AI and can combine them around the work in front of you.

"But I’ve barely used AI. Am I invited?"

Yes. You don’t need to be technical.

You need to be curious, willing to bring real material, and comfortable having an actual conversation with the machine rather than accepting its first answer like a royal decree. Most RobotsOS systems ask questions, explain what they’re doing, and guide you through the process. If you can upload a file, answer honestly, and say “no, that isn’t what I meant,” you’re ready.

If you’re a paid member and don’t know where to begin, tell the RobotsOS Advisor what you’re working on. It can help you find a sensible first robot or combination of robots.

Your five-minute way in

You just want to try something. Right now. Here’s what to do.

1

Pick one real thing you care about today: a question, a draft, a decision, an idea, or a piece of work that isn’t quite behaving.

2

If you want to explore, start with whichever RAMH piece catches your attention. If you want help working on the thing in front of you, ask the RobotsOS Advisor where to begin.

3

Bring the real material with you. The robots are much more interesting when they have something specific to look at.

4

Talk back. Disagree. Add context. Ask why. See what changes.

Already comfortable working inside your AI? You can also connect Robots MCP and ask: “How can I use Robots, and what is available to me?”

That’s your way in. You do not need to understand the whole ecosystem before you use one useful part of it.

Frequently Asked Questions

"Which AI can I use with RobotsOS?"

Most RobotsOS systems are portable and can work with Claude, ChatGPT, Gemini, and other capable AI environments. If your AI supports MCP, you can also connect Robots MCP and call compatible systems directly. Some larger robots still need to be downloaded and set up in your environment.

"I’m not technical. Will the robots make me feel stupid?"

No. They’re conversations, not coding assignments. They ask questions in ordinary language, explain what they need, and guide you through the method. You’re allowed to interrupt, disagree, ask why, and change the direction. In fact, please do.

"What if I use ChatGPT instead of Claude?"

That’s fine. Most RobotsOS systems are portable across capable AI environments, and each robot will tell you if it prefers a particular setup. If your AI supports MCP, compatible systems can come through Robots MCP too.

"How is this different from the free newsletter?"

Free RAMH gives you complete essays and experiments designed to change what you notice, understand, question, or want to try. Paid RAMH takes selected problems further and gives you access to the applied side of the publication: the methods, systems and specialist collaborators inside RobotsOS, plus Robots MCP.

The paid promise isn’t simply more content. It’s deeper access to the working intelligence behind RAMH.

"I subscribed but I don't know where to start."

Ask the RobotsOS Advisor once you log in. Tell it what you’re working on, what keeps going wrong, or what you wish AI could help you do. If you’ve connected Robots MCP, you can also simply ask: “How can I use Robots, and what is available to me?”

"What if I get stuck?"

Ask the RobotsOS Advisor, leave a comment on the relevant post, or tell me where you got stuck. I read the comments, and the humans here are unusually generous with one another. Nobody gets thrown out of the house for uploading the wrong file.

One last thing

You don’t need to arrive with a perfectly organised brain, a five-year plan, or a beautiful AI workflow.

Start with something you genuinely care about enough to follow. Around here, a question can stay a question for a while, become an essay, turn into an experiment, or eventually earn itself a robot.

The robots can wait until they’re useful.

To new friends who found the robots,

Mia

© 2026 ROBOTS ATE MY HOMEWORK. All rights reserved.