How to do anything with AI (parent friendly)

Most people today use AI like it's Google. They type in a question (maybe upload a file or two), read the answer (or get a file back), and that's about it. And when I say most people, I mean pretty much anyone outside the San Francisco tech bubble. They have no idea what AI can actually do today, or how much real work it can get done for them (it's probably 95% of what they do manually all day).

My non-technical friends, colleagues, and even a few investors have asked me to teach them how to use AI properly, I try my best, but limited by how much time I can spend personally with them. I had my whole family onboarded onto Instinct, and I saw them in real time have a spark of the future.

Meanwhile, my dad sent me a link to a $$$ course to "learn agentic AI for architecture". I'm sure grifters have come up with something different for each field. The fact is, you can do practically everything you want with a $20 ChatGPT or Claude subscription and the app that comes with it and completely figure it out yourself (I think of it like learning how to use a computer, I'm sure there were some people who actually went to a 'computer class' but most of us just got a hang of it on our own). AI is the exact same, you do not need a class for it, you do not need a "special computer", you can just get started.

This blog is an attempt at getting anyone young-or-old, employee-or-business owner, get immediately started with agentic AI, and meant to be something you can forward to your parents/colleagues/children to ensure they don't get left behind in embracing this life changing technology.

Go through this yourself, and understand and absorb it before you pass it ahead. Do not delegate it off to someone in your team if you're a business owner, or don't ask your kids to figure it out for you. Try it out yourself. Spend time with it. That's the only way this works.

What people get wrong about AI

Before we set anything up, let me clear up five things I hear all the time (usually right before someone decides AI isn't for them).

Misconception	Reality
"Codex and Claude Code are for programmers."	They have "code" in the name because developers were the first people using them, but they're really an AI that can take actions on your computer, and you talk to them in plain English. If a task needs code, they write and run it on their own (the same way you use Excel every day without any idea how it was programmed). Some of the most useful things I do with them, like turning a folder full of invoices into one clean spreadsheet, involve zero code on my end.
"I need a specialized AI tool for my kind of work."	You almost never do. Nobody buys one computer for their finance work, another for sales and another for legal. You use the same one for editing Word documents, sending emails, building financial projections and posting online, and AI is the exact same: one general agent, your files, and a few skills (more on those later).
"AI hallucinates a lot."	A lot of people's opinions on this are based on models from 1 or maybe even 2 years ago, which could only answer from memory, so when they didn't know something, they'd make up an answer and say it with full confidence. The models from the past 6 months are extremely good, and when the agent is working on your real data, your actual spreadsheets and documents, a hallucination is a rare exception. Honestly, when it comes to making something up, you can trust the agent more than a human.
"AI is all slop."	You've probably seen articles online that sound like complete slop, or images that are so obviously AI-generated. By default, the AI gives you what it feels is the average answer, so if you put in no effort, slop is what you get. Give it examples of the way you write and what you consider good, iterate on what it gives back, and you'll get exactly what you want. It's also a one-time thing. I have one set up that writes emails the way I used to write mine, and there's no reason for me to not trust it, it's like a personal assistant who conveys what I want to the person on the other side.
"It's not reliable, it'll mess things up."	At first it will mess up, same as any new hire, but there's always a reason behind it, usually some context it was missing. You find that, you fix it, and you move on. Improving your skills based on that feedback is how you'd onboard anyone onto your work, and it's how you get an agent aligned with your taste, your way of working and your style. That's when it becomes reliable.

Okay, what can you do with AI?

People ask me all the time, "Can I do this workflow with AI?" or "Can AI take me from A to B?" Unless it has something to do with the physical world, like physically moving something, the answer is almost always yes. It's just about building the system to be resilient enough to get there, whether that's by prompting it well or setting up a skill. Anybody who's telling you it can't be done, or that you need something else for it, isn't familiar with what's happening in the industry or with the latest models.

Some ambitious examples:

1. Managing your entire social media presence, from generating posts and editing videos to managing relationships with partners.
2. Running the entire operations of a financial accountant, from running Tally (or whatever accounting software you use) to raising and managing invoices, figuring out billing issues and coordinating with government departments.
3. Running your entire legal for free, reviewing contracts, editing them and doing redlines.
4. Being your personal health assistant. This is one I use myself (maybe I'll write about it later). Mine is connected to my Whoop, my meal service and my BCA (body composition) scanner, so it has live data on my health all the time. I can ask it anything and program my fitness accordingly.

The basics

You don't need to understand how AI works to use it (most of us have no idea how our computers work either, and we use them all day), but three ideas will make everything after this make a lot more sense.

What AI is, tokens, and cloud vs local

What AI actually is

ChatGPT and Claude run on what's called a large language model. It's been trained on an enormous amount of text (think a good chunk of the internet), and it learned to predict what comes next so well that it can reason, write and follow instructions.

The way I'd explain it to my parents: a model on its own is a brain in a jar. It can think, but it can't touch anything. An agent is that same brain with hands, meaning access to your files, your browser, your email, and the ability to run programs. The app you install is what gives it those hands, and people in tech call that the harness.

Tokens

AI doesn't read words, it reads tokens, which are small chunks of text (roughly, a token is about three quarters of a word).

Everything costs tokens: the messages you send, the files it reads, the answers it writes, and that's what your subscription is actually measuring. In practice this means two things. Huge files and very long chats burn through your limits faster. And each chat can only hold so much at once (that's called the context window), so when a chat gets really long it starts forgetting the early parts, a bit like a meeting that's been going on for three hours. When you start a new task, start a new chat.

Cloud vs local

The AI model itself runs in the cloud, on OpenAI's or Anthropic's servers. The app runs locally, on your computer. So the app is the bridge between the two: the brain is in the cloud and the hands are on your machine, which is exactly why you'll want the desktop app and not the website (more on that in the setup). It's a bit like your email, which lives on Google's or Microsoft's servers, but you read it, write it and attach files to it from your own computer.

It also means whatever the AI reads gets sent to the provider. Coming from security, I'd do one thing here: go to data controls in settings and turn off the option that lets them train on your chats (if you don't want that). And if something is genuinely sensitive, check your company's policy before you put it in.

You might also hear about "local models", which run entirely on your laptop. They exist, but they're a lot weaker than the cloud ones and need a powerful machine, so for everyday work you can skip them.

Do this exactly

1. Download the desktop app, not the website. Get the ChatGPT desktop app on your computer (Claude's desktop app works exactly the same way, if you'd rather use that). The website can only chat with you. The app can actually work on your computer: it can open your folders, read and edit your files, use your browser, and run things for you (which is pretty much everything in this guide). It's the difference between calling someone for advice and having them sit at your desk and do it with you.
   • Don't let the interface scare you. Show a computer to someone who has never seen one and the keyboard alone would intimidate them, but today it's second nature for practically everybody with a desk job, and this is the exact same thing. You'll see words like Codex, agent, skills and terminal, and you can ignore all of them for now. (When I set my family up, the first thing that threw them was the sheer number of buttons and settings, and the fix was just telling them to ignore everything except the chat box for the first week.) You'll be talking to it in normal English the whole time, the same way you'd message a colleague.
2. Buy the $20 plan. The free version doesn't give you access to any useful agentic capabilities. Start with $20, that can be your starting budget. If you use it properly, you will get orders of magnitude higher return out of this than you invest, and you'll invest more yourself as you see the value out of it.
3. Talk to it, don't type. Consider purchasing and installing Wispr Flow, or just use ChatGPT's voice option. I've been typing my whole life and I'm at around 120 WPM, but it still constrains the flow of thought in your mind. AI is very good at understanding what you're saying, so I often blabber about a task for 10 minutes and just send it to the agent, which actually works really well. You get to explain everything freely and naturally, and it picks up exactly what you want.
4. Turn on computer use. This lets it see your screen and click and type in other apps the way you would. It's slower than its other tools, but it means it can work in apps it otherwise couldn't get into. You can enable it in the settings.
5. Connect your apps. Gmail, Google Calendar, Drive, Slack, Notion, whatever you use every day. Every connection is one less thing you have to copy and paste into it.
6. Make a project for your work. Think of a project as a workspace, like a folder on your desktop. Let's say you define everything about your company in one project. You open one chat for a sales task, like a proposal for a customer, and then another for a marketing task, and both already know you're working on this company, so you're not re-explaining who you are and what you do every single time. I keep separate ones for BugBase sales, finance, legal and my personal stuff. Any new chat you start in a project has the overall context of:
   • the folders in the project
   • what was going on
   • a brief chat history
   • a bit of memory
   • whatever is written in the AGENTS.md file (a plain text file where you describe who you are, what you do and how you like things done)
   • any other relevant files connected to it
7. Understand the different types of models. There are a bunch of models to pick from, and most of them also come with thinking levels (how long they think before they answer). The logic is simple: go smarter than the basic one, but not the smartest in the world, that's just overkill. You're not solving cancer with the work you're doing (if you are, sure, go all out). In my opinion, GPT-6 Sol and Opus 5.5 on medium or high work extremely well today, out of the box, for any task in existence. Lower models may sometimes work and are slightly cheaper and faster, but their intelligence isn't guaranteed, so I just don't use them, and I still get most of my work done.
8. Give it full permissions. Out of the box, it asks you before every single tool call, every file it opens and every command it runs (imagine an assistant who checks with you before opening every single email). These tool calls are very technical, and if you're non-technical you won't really be able to tell whether it's doing what you want anyway, so all the prompts do is slow you down. Put it on full, complete access. It will warn you that this is dangerous, and that's totally okay. The models are really good, and the chance of them doing something bad is so low that I haven't seen it happen to me with the latest models. If you're worried about it making a payment or deleting something, those approvals are different from tool permissions. The people building these models and apps are aware of that and have built it into the training, the system instructions and the apps themselves, so it stops and asks for your approval in exactly those situations.
9. Turn on fast mode, and be patient. I noticed many of the folks I introduced to agentic AI weren't very comfortable with the fact that some tasks take 2 to 3 minutes, and sometimes even an hour. This is normal, and expected. Agentic AI consumes an order of magnitude more tokens than a normal ChatGPT session, and the GPUs are split amongst all their users (with dedicated GPUs you'd get very fast inference), so it ends up slightly slower. It's also doing tool calls, which means it's actually interacting with your computer: things are loading, it's looking at the output, validating it, thinking about it, and that takes time. You have to accept that. You can turn on fast mode to speed things up, but it will eat through your usage quicker. I keep fast mode on all the time.

Limits and resets

The plan isn't unlimited. Usage is counted in windows: a short one that resets every few hours, and a weekly cap on top of that. You can check where you stand in settings.

When you hit one, you can wait for it to reset, switch to a smaller model for simpler stuff, or upgrade if it keeps happening.

Try these today

If you're not sure where to start, here are five things you can paste in during your first hour:

1. "Look at my Downloads folder. Sort everything into sensible folders and tell me what you moved."
2. "Read my unread emails from the last two days. Tell me which ones need a reply from me today, and draft those replies. Don't send anything."
3. "Here are photos of my receipts from this month. Put them in a spreadsheet with date, vendor, amount, and category, and total it by category."
4. "I'm choosing between X, Y, and Z. Research them, compare price, pros and cons, and reviews, then give me a table and a recommendation."
5. "Here are my rough notes from a call. Turn them into a clean follow-up email and a one-page proposal."

You'll notice none of these are questions, they're all tasks, and they're the exact same tasks we all learned to do on a computer (files, emails, spreadsheets, research, documents), except now you're handing them off instead of doing them yourself. That's the biggest shift I'd want you to make: stop asking AI things and start handing it work.

Making it work for you

Once you're set up, these two are what take it from a smart chat window to something that actually does real chunks of your work for you (think of the one person in every office who learned keyboard shortcuts and Excel formulas, and suddenly did in ten minutes what took everyone else an afternoon).

Skills

A skill is a set of written instructions that teaches the AI how you like a specific task done. It's just a text file called SKILL.md, and it says something like "When I ask for a proposal, use this template, this pricing and this tone, and check these things before you finish." It's basically the onboarding doc you'd give a new hire, except you write it once and from then on that task gets done your way every time, without you explaining it again.

The best part is that you don't even have to write them yourself. Do the task with the AI once, correct it until it's right, and then tell it to "turn what we just did into a skill."

At BugBase, I have skills for our commercial proposals, for reviewing customer contracts against our standard positions, for our monthly finance reports, and for filling out the security questionnaires customers send us. Each of those used to take up a few hours of someone's week.

Scheduled tasks (cron jobs)

Engineers have had cron jobs forever, which are just tasks that run on a timer (like a recurring reminder on your calendar, except the AI actually does the thing instead of just reminding you). Now you can set them up yourself, in plain English, and most of the time what you're triggering on that timer is one of your skills, so it gets done your way:

• "Every weekday at 8am, go through my email and calendar and give me a one-page brief of my day."
• "Every Monday, pull last week's numbers from this sheet and draft the update for the team."
• "Every Friday, check these three competitors' websites and tell me what changed."

Once you have a few of these running, a good chunk of your routine work happens without you having to kick it off.

Advanced: agents

An agent is the step after all of this. Instead of you sitting in the chat handing it tasks, it runs whole parts of your work on its own, and you reach it the way you'd reach a person. Setting one up is still, unfortunately, slightly technical today, but it's very doable, and it works.

Go deeper into agents

Up to this point, you've been doing the work with AI, sitting in the chat, giving it tasks, checking what comes back. The advanced step is realizing you are the operator now, and you don't have to be in the chair for every single task.

Once you've refined a skill to the point where you're confident that just running it works well every time, you can hand that whole process off to an agent. Let's say you want to put out a blog post every week, and your blog skill is always putting out really good drafts. It still needs your review once, but it's really good. That whole process (picking the topic, researching it, writing the draft in your voice, putting it in a doc for you to look at) can be delegated to an agent that runs it on its own and only comes to you at the end.

The easiest way to think about an agent is as another human being entirely. When you hire someone, you give them:

• a job to get done (the goal)
• an onboarding doc on how you like things done (the skills)
• access to the tools they need, and nothing more (the connections and permissions)
• a routine (the schedule)
• a way to reach them, like an email address or a phone number (the channel)
• a manager who reviews their work before it goes out (you)

An agent is exactly that, it's skills and scheduled tasks put together with a goal, running without you sitting there.

The channel is the part that makes it feel like a person. Instead of opening an app every time, you make the agent available to you where you already are: you give it its own email address, or a way to talk to it over Telegram, WhatsApp or even iMessage. You message it the same way you'd message a colleague, forward it an email or a voice note from your phone, and it messages you back when it's done or when it's stuck. Instinct is one of the more popular agents that came up recently (it's the one I got my whole family onto), and it's a good example of exactly this: something that works like a person you can just message.

And just like a real team, you can have more than one: one that preps your morning brief, one that drafts the weekly update for your investors, one that finds unpaid invoices and drafts the reminders. Of the 8 I run, the morning brief is the one I'd start with, it's waiting for me every day before I've even opened my laptop.

The rule I'd stick to is the same one you'd use with a new employee. Start them on low-risk work, review everything at first, and only stop checking once they've earned it. Anything that moves money, signs something, or goes out under your name still comes to you first.

Setting one up. Running your own agents means setting up something like OpenClaw or a Hermes agent, which is slightly more complicated and, unfortunately, still slightly technical today. It's still very doable, and it works, I have 8 agents running myself.

Between the two, Hermes agent is what I would strongly recommend you set up. OpenClaw feels unnecessarily sloppy to me today, but if you're completely non-technical, OpenClaw might be the way to go. And you don't have to figure out either one on your own: ask your agent, your ChatGPT or your Claude Code to set it up for you, or to teach you how it has to be set up and what all has to be configured, in very simple baby terms.

That's it

Think about how much learning to use a computer changed your work. Your finance, your sales, your legal, editing documents, sending emails, building projections, talking to people and posting online, practically everything you do runs through it now and nobody thinks twice about it. AI is that same shift happening all over again, and it's happening right now.

You do not need a $$$ course, you do not need a different tool for every problem, and you do not need a developer. Everything in here is already sitting inside a $20 app you probably have and aren't really using. Install it, spend 15 minutes setting it up, and give it something real to do today. And if this helped, forward it to someone who's still using AI like Google (your parents are a great place to start).

Two last notes

The interface may change in the future, like the ChatGPT UI today and 3 days back was different. They change it so frequently, similarly with Claude Code, but if you understand this, you will be able to understand every single thing that they add on top of it. In fact, you don't even need any additional features they add for this to be insanely life changing for you.

And I don't want to be a doomer, but it is possible that eventually AI models get so good that the expertise you bring in orchestrating them isn't necessary anymore, and they're just able to do most tasks out of the box. Many AI companies today are already buying data on how these workflows are run (the same work many people get paid for today) to improve their models on them. In my opinion, there's an opportunity of maybe a year where this is still useful, and after that it's not guaranteed. So get onto it fast.