Tag: Productivity

  • Automate Yourself Out of a Job – Step One – Learn the Prompt

    Automate Yourself Out of a Job – Step One – Learn the Prompt

    Introduction

    Everybody and their mother is talking about AI these days. Will it take our jobs? Honestly, I say: great! Let AI take all the boring stuff I don’t want to do anyway.

    Now, before you think I’ve lost my mind, let me clarify: I’m a co-owner of an e-commerce store. And, like most small business owners, my day-to-day is filled with tasks I’d rather not touch—but someone has to do them. I can either hire people (which we currently don’t have the budget for) or grind through them myself. Spoiler: I’ve been wearing my big-boy pants and doing the grinding.

    But here’s the thing: I don’t want to grind forever. My dream is to grow this company into a giant, profit-churning machine. Until that day, I’ve got two options:

    1. Accept that these tasks are my life until we hit the big leagues.
    2. Automate the living hell out of my company.

    Guess which one I’m picking?

    That’s right—automation all the way. Either I’ll fully automate most of the boring stuff I do now, or at least partially automate it so I can finish faster or hand it off to someone else without a second thought.

    So, in the spirit of New Year’s resolutions, I’ve decided that 2025 will be the year I automate everything that makes sense to automate. And I’m documenting the whole journey for the internet because… why not?

    Here’s the thing I’ve learned after using AI for about a year in my business: everything starts with a prompt. If you don’t know how to talk to AI, you’ll struggle to get meaningful results. That’s why step one of my automation journey is all about mastering the art of prompting. Let’s kick things off by demystifying how to talk to AI and building a rock-solid foundation for everything that comes next.

    What Is a Prompt, and Why Does It Matter?

    The prompt is basically what you tell the AI—simple as that. Open a ChatGPT window, type something into the chat box, and boom: that’s your prompt.

    But why does it matter? Think of it this way: imagine the AI is a real person, and you need something from them. What do you do? You explain what you want. Clear communication is key.

    Here’s the catch: AI isn’t a person—it’s a machine. It doesn’t inherently understand nuance or context unless you explicitly provide it. The better you communicate, the better your results. The more context you give about the task, the higher the quality of the output you’ll get.

    It’s a simple concept: the quality of what you put in directly impacts the quality of what you get out.

    Tips for Writing Better Prompts

    To get the best results, there are a few key things to keep in mind:

    1. Be Specific About What You Want
      Start by defining your goal. I like to call this the “done state.” What does the finished product look like? For example, if you’re asking the AI to write an email to a client, your done state is a ready-to-send email that you can copy and paste.
    2. Provide Context
      The AI needs to know the “who” and “why” behind your request. Who is the email for? Why are you writing it? The more details you provide, the more tailored the response will be.
    3. Give It a Persona
      AI works better when you tell it who it’s acting as. In the email example, you might ask it to act as you. Tell it who you are, your tone, and anything else relevant to your “voice.”
    4. Specify the Format
      Want a list? A table? A formal email? Tell the AI exactly how you want the information presented. The clearer your instructions, the more accurate the output.

    When you provide all these details—your goal, context, persona, and format—the AI knows what you expect, and the chances of getting a great output increase dramatically. Without this information, your results are a gamble: sometimes good, sometimes way off.

    The Building Blocks of a Good Prompt

    One thing upfront: I don’t think the order of these steps makes a big difference. Depending on your thought process, you can adapt the framework and go with what works best for you. That said, here are the key elements to building a solid prompt:

    Give it a Persona

    I like to start by giving the AI a persona. Think of it as an actor, and you’re the director telling it what role to play. For example, you could say:

    • “You are the General Manager of a Fortune 500 company.”
    • “You are a Marketing Content Creator specializing in email campaigns.”
    • “You are a Chef crafting a menu for a Michelin-starred restaurant.”

    By defining a role, you set the stage for the AI to approach the task with the right perspective.

    Be Specific About What You Want

    Now, tell it exactly what you want it to do. Don’t just say, “Write an email.” Be clear about what kind of email and how it should look.
    For example:

    • “Write an email inviting [recipient] to a meeting on January 20, 2025, at 4:00 PM.”

    The “done state” is clear: a written email with a suggested meeting.

    Provide Context

    Once the AI knows its role and the task, give it some background.
    For example:

    • Who is the email for—a colleague, a client, or a potential partner?
    • Why are you sending this email? Is it to schedule a meeting, close a deal, or introduce yourself?
    • How formal or casual should it sound?

    Context is the glue that holds the task together, ensuring the AI’s response is relevant and aligned with your expectations.

    Specify the Format

    How should the output look?

    • Do you want a simple block of text?
    • A list of meeting date options?
    • A table summarizing key points?

    For example, you could say:

    • “Create a bullet-point summary of the last meeting’s discussion.”
    • “Include a table of suggested dates and times for the meeting.”

    Reference Existing Work

    This step isn’t always necessary, but it can be a game-changer when it is.

    • If you have a reference email, paste it into the prompt. For example: “Here’s a sample email I like. Format the new email similarly.”
    • If you’re creating something like a product description, you could share a well-written description as a guide.

    References give the AI a benchmark to emulate, which can dramatically improve the quality and consistency of the output.

    Structure Your Prompt Clearly

    Lastly, structure your prompt so it’s easy to read and understand—both for the AI and for you if you come back to it later.

    • Use Markdown or a simple format with headings and sections.
    • Clearly separate references or context from instructions.

    Why does this matter? A blob of unstructured text is confusing for the AI and frustrating for you to revisit. Clean formatting makes prompts reusable and easier to tweak.

    With these building blocks, you can craft prompts that set the AI up for success, giving you better and more consistent results. A little extra effort upfront saves a lot of time (and frustration) later on.

    Iterating for Success

    Now, for my absolute favorite part: iteration.

    Some modern large language models (LLMs) have pretty big context windows, which means they can “remember” a lot more information within a single conversation. One of the best ways to use this is for iteration—refining outputs step by step until they’re just right.

    Let’s say you’ve crafted your nearly perfect prompt, but something is still missing in the output. What should you do? You could go back and tweak the original prompt and try again—especially if you’re planning to save it for future use. However, my go-to approach is to iterate directly within the same chat.

    What Is Iteration?

    Iteration is simply the process of asking the AI to refine or adapt its output based on your feedback.

    • Did it write an email, but leave out a key detail? Ask it to add that detail.
    • Want the tone to be more professional—or maybe throw in a joke? Tell the AI to rewrite it with those changes.
    • Need it formatted differently? Ask for a bullet-point summary, a table, or whatever you need.

    The key here is to keep the chat window open and use the same context. You can go through this process as many times as needed until the output meets your expectations.

    Get the AI to Teach You

    If you had to iterate a lot, here’s a pro tip: ask the AI to generate a “perfect prompt” based on the final version of the output.

    • This gives you a better idea of what you could have done differently in the original prompt.
    • You can also save this AI-suggested prompt for future use.

    Let the AI teach you how to better talk to it—it’s like a built-in feedback loop!

    A Word of Caution: Always Evaluate

    Never send out AI-generated content—emails, reports, or anything else—without reviewing it first.

    • Always fact-check the details. AIs can hallucinate or add incorrect information.
    • Carefully review the tone and content to ensure it matches your expectations.
    • Triple-check everything before hitting “send.”

    Iteration is powerful, but human oversight is critical to make sure the output is accurate and aligns with your goals.

    By iterating within the same context and refining as you go, you can take AI-generated content from good to great—and, in the process, become even better at crafting effective prompts for next time.

    Conclusion

    How does all this help in automating myself out of a job? Honestly, not that much—yet. I still have to do a lot myself. But it does speed me up, and more importantly, it’s the foundation for everything that follows. Without mastering the prompt, the rest of the journey wouldn’t be possible.

    Now that the first step is done, it’s time to take a specific part of my job and figure out how to make it as fast and organized as possible. Stay tuned—I’ll be documenting that process here, too.

    If you haven’t already, try this out for yourself. It might seem overwhelming at first, but it’s really not. I don’t even think about all the steps anymore—I just keep the basics in mind, write my prompt, and iterate as needed. Whether it’s for repeatable tasks or one-off content, the key is to start and refine as you go.

    As with everything, if the basics are sound, the rest becomes much easier. So go out and test, test, test. The age of AI is here to stay. Jump on the train now, and you’ll be ahead of the game. Wait too long, and you might get left behind.

    See you next week (hopefully)!

  • How I Use AI to Supercharge My Work

    How I Use AI to Supercharge My Work

    Introduction

    AI is here to stay. It’s not just the future—it’s already here, usable, helpful, and my secret weapon for juggling three businesses, spending quality time with family, and staying healthy.

    In this post, I’ll share practical, real-world ways AI can boost productivity, spark creativity, and accelerate learning. These aren’t hypothetical use cases—they’re how I genuinely use AI every day, and it’s a game-changer if you know how to wield it.

    I’ll walk you through how I use AI for creative problem-solving, how it’s helping me learn to code (a work in progress), and how it keeps me sane while managing what feels like 20,000 things at once. So strap in, get focused, and let’s dive in.

    Why AI?

    When ChatGPT first launched, I was immediately intrigued. I dabbled here and there, but wasn’t really doing anything useful with it. Then, in April 2024, I shifted focus from one of my businesses—a POS agency—to our other “child,” an e-commerce store. That’s when AI went from being a fun experiment to an essential tool.

    Let me set the stage: we have a ton of Amazon listings (about 3,000, to be exact) and an online store that was, quite frankly, thrown together “on the knee.” The product descriptions? Well, let’s just say they were written by a couple of clueless guys (me and my business partner) who had zero understanding of SEO, keywords, or how to structure a good listing. We were basically listing products like a couple of crazy monkeys.

    Fast-forward to today, and I’m trying to fix this mess. Learning about SEO and keyword optimization has been eye-opening, but here’s the problem: I’m one person, and writing 3,000 well-optimized product descriptions by hand would take years. This is where AI comes in. Our product catalog is relatively uniform (we mostly sell cables), which makes it a perfect use case for AI to step in and help create structured, optimized content at scale.

    Another area where AI has been a game-changer is learning to code. If you’re a noob like me—with no friends, mentor, or anyone to ask for advice—AI is a godsend. Let me be clear: AI shouldn’t write the code for you, but it should write code with you. That’s where it excels. It helps you learn by building something useful, correcting mistakes, and explaining concepts as you go.

    And then there’s brainstorming—my third favorite way to use AI. Whether it’s writing a blog post, coming up with a business idea, or just bouncing thoughts around, AI is an incredible sounding board. By describing your idea in a prompt and asking for feedback or suggestions, you gain a fresh perspective. It validates your ideas, offers alternatives, and sometimes sparks entirely new ones. It’s like having a partner who’s read everything humans have ever written.

    Real-World Use Cases

    Why Use AI for Amazon Listings?

    AI excels at repetitive tasks, and it’s a lifesaver when you want to expand your reach. Let’s say you start with one product on Amazon, but eventually, you think, Man, maybe I should boost my sales by listing it on eBay or creating my own online shop.

    You could just copy-paste your Amazon descriptions, but there’s a catch:

    • Google doesn’t love duplicate content, and copy-pasting could hurt your search rankings.
    • Platforms like eBay and online stores have different formatting requirements than Amazon.

    For example, eBay’s product descriptions allow for HTML and CSS, meaning you can essentially create a mini webpage within the description. Most people (myself included) just buy a ready-made template and add their own pictures and text. But here’s the problem: your Amazon description might be too short, leaving the eBay template looking half-empty, or too long, making it look cluttered and out of place.

    This is where AI shines. Simply ask the AI to make your description shorter or longer, and voilà—you have a perfectly adjusted version. Of course, it’s crucial to proofread and adapt the output to make sure it fits your needs. But within minutes, you’ll have platform-specific descriptions ready to go, saving you hours of manual editing.

    Here’s how I do it:

    Give the AI all the info you have about the product. Ask it to make you five catchy bullet points for Amazon, focusing on unique selling points or advantages your product offers. Then, have it generate five more so you have options to choose from.

    Work through them one by one—pick the ones you like, adapt them yourself, or ask the AI to refine them further (e.g., “Add this,” “Remove that,” “Rephrase this”). By the end, you’ll have way better bullet points than anything I could have written solo.

    Do the same for the description. Go sentence by sentence, rewriting, adapting, and refining. Use AI to polish every part, and before you know it, you’ll have professional-grade content that’s optimized for each platform.

    AI Code Assistance: A Mentor in Your Pocket

    AI is like having a mentor in your pocket—always there to answer your questions, no matter the time. If you’re learning to code, like I am (and let’s be honest, there’s always more to learn), AI can be your most trustworthy partner.

    Imagine this: you’ve spent 20 minutes trying to figure out a bug in your function. Print statements everywhere, nothing’s working. Frustration is building. Fear not—your AI mentor is here. Just describe the problem, explain what you expect to happen versus what’s actually happening, paste the code, and boom. Nine times out of ten, you’ll get a solution or at least an idea that points you in the right direction.

    My Rules for Using AI While Learning

    Here’s the deal: if you’re new to coding and really want to learn the craft, you need to put in the work. AI can’t learn it for you—it can only help you along the way. So, follow these rules:

    1. Write Your Own Code
      You need to actually write your own code. If you’re a pro with 10 apps under your belt (and no, a calculator or to-do app doesn’t count), then sure—go ahead and use tools like Copilot to generate boilerplate code. But if you’re still learning, resist the urge. Writing your own code, bugs and all, is how you learn.
    2. Search First, Ask Later
      Don’t jump to AI for every little question. Spend at least 20 minutes searching the docs or Googling for the answer. This is how you build problem-solving skills and retain knowledge.
    3. Debug Like a Pig Searching for Truffles
      When you hit a bug, take the time to figure out what’s happening. Write down what you expect to happen versus what’s actually happening. Go through your code line by line. Spend 20–30 minutes (or even longer) trying to solve it yourself. That struggle is where the real learning happens. Only after you’ve tried everything should you turn to AI.
    4. Write All the Boilerplate
      Yes, it’s tedious. Yes, it’s boring. But until you’ve written it a thousand times and understand why it’s there, you shouldn’t automate it. Once you know the boilerplate inside and out, then—and only then—can you let AI take over.

    AI is a fantastic partner on your learning journey, but it’s just that—a partner. The newer you are, the less you should rely on it. Use it to guide you, to teach you, and to help you think, but don’t skip the hard work. That’s where the magic happens. Trust me, it’s worth it.

    Brainstorming: Lift the Storm in Your Brain

    I’ve got a ton of ideas—businesses, blog posts, a YouTube channel about everything from Linux to gaming, coding, and AI. But let’s be real: does every idea make sense? Hell no! That’s where your AI brainstorming buddy comes in.

    Here’s how to do it: State your idea, your goal, and your initial thoughts to the AI, and let it give you feedback. Sounds simple, right? But there’s a catch: AI is wired to be positive—it’s trying to be likeable. If it shot down every half-baked idea you tossed its way, you’d stop talking to it pretty quickly, wouldn’t you?

    So, here’s how to use it right. The real magic isn’t just in the AI’s feedback—it’s in the process of describing your idea. Writing it down forces you to think. It makes you clarify your thoughts, refine your idea, and see potential pitfalls or risks. AI might encourage you or even point out things you hadn’t considered, but ultimately, the vetting process is on you.

    Remember, you’re the operator, the driver. You already have the most powerful computer on the planet—your brain. Use AI to enhance the storm of ideas swirling in your head, adding some magic to help verify which ones are worth pursuing and which are better left on the drawing board.

    Examples of My Personal Brainstorming Sessions with AI

    1. Blog Post Ideas:
      Generating topics like “How I Use AI to Supercharge My Work” and outlining its structure.
    2. Business Positioning:
      Refining niche selection strategies and defining target audiences for products like extension cables.
    3. Product Optimization:
      Brainstorming approaches to improve Amazon listings and adapt product descriptions for multiple platforms.
    4. Coding Projects:
      Validating features and structuring ideas for web apps, like creating dynamic forms or managing persistent filters in Django.
    5. Personal Branding:
      Crafting taglines, such as “Serial Entrepreneur, Code Monkey, AI Enthusiast,” and brainstorming ideas for a logo and branding.

    Benefits of AI Tools

    Save Time

    No matter what you’re working on, having a sidekick to help you refine your ideas can be a game-changer. Here’s how I do it: I write down what I want to say, quickly and without overthinking—just a brain dump of everything that comes to mind. Then, I let AI step in to refine, reorganize, and make it readable.

    I’m no professional writer (duh), and English is my third language (double duh), but that doesn’t stop me from creating something worth reading. The AI helps me turn my messy drafts into something polished, saving me hours of editing while still keeping my voice intact.

    This approach isn’t just for blog posts—it works for emails, product descriptions, or even meeting notes. Write fast, let AI clean it up, and move on to the next task without wasting time on perfectionism.

    Boost Creativity

    Need to prepare a presentation but don’t know where to start? Staring at a blank page, trying to craft the perfect response to a client’s tricky email? Don’t panic—just start talking to your AI buddy. Even if the answers aren’t 100% perfect, the act of brainstorming with AI can loosen the knots in your head and get the ideas flowing. No more blank-page paralysis.

    Have several ideas for solving a problem but can’t decide which one to go with? Talk it through with AI. It won’t make the decision for you, but it can help clarify your thoughts, lay out the options, and sometimes even uncover ideas you hadn’t considered.

    Thinking about starting a newsletter for your clients but have no clue how to begin? Let AI give you a starting point. It might suggest a structure, topics, or even a first draft to get you on the right track. From there, you can tweak and refine, building on the foundation it provides.

    AI isn’t just a tool—it’s like having a creative partner who never gets tired or runs out of ideas. It’s not about perfection; it’s about momentum. Once you get started, the rest becomes easier.

    Accessible to Everyone

    AI empowers anyone to start creating, learning, and brainstorming—no matter their background or expertise. You don’t have to be a professional writer to produce a well-structured, good-enough outcome in a fraction of the time.

    Whether you’re crafting an email, writing product descriptions, or planning a presentation, AI can help you get started, refine your ideas, and even guide you through unfamiliar tasks. And the best part? It’s not limited to any specific profession—there are benefits waiting for everyone, from entrepreneurs to students, to uncover.

    But here’s the thing: like any tool, AI requires practice to use effectively. Prompting is a skill you have to learn. It takes a bit of trial and error to figure out how to phrase your requests and guide the AI to produce the results you’re looking for. Give it time, experiment, and you’ll quickly see how it can enhance your work.

    Challenges and Misconceptions

    1. Reliance on AI

    I know I sound like a broken record, but don’t let AI take over completely. It’s tempting to let it generate everything from scratch and call it a day, but that’s the fastest way to produce content no one wants to read. Worse, you’ll switch off your brain entirely and learn nothing. If all you create is generic, what’s the point of you?

    Solution: Use the tool—don’t let the tool use you. That’s why I’m a fan of “dirty” writing. Don’t stress over perfection or commas; just let your creative mind flow. Write what you want, how you want, and let AI refine it. This ensures you’re thinking critically and staying in control while AI enhances your work.

    2. Ethical Concerns

    Let’s face it: the data AI is trained on isn’t always “free” or ethically sourced. This is a billion-dollar business, and AI models are built on whatever they’re fed, whether they had permission. If this bugs you, you might feel inclined to boycott the technology—but don’t expect it to last long. Soon, even your toaster will probably have AI just because it can.

    3. Imperfect Outputs

    Here’s another big issue: AI is fantastic at making things sound right, even when they’re utterly wrong. If you rely too heavily on it, you risk-taking everything at face value without questioning its validity.

    Solution: Always double and triple-check the outputs. Be critical and ensure the information is accurate before using it.

    Tips for Success

    • Better Input = Better Output: The clearer your prompts, the better the results. Provide enough context, and don’t hesitate to tweak your approach.
    • Be Clear: Be specific about what you want, and if possible, provide example outputs or multiple directions to explore.
    • Iterate and Experiment: If the first output is subpar, rephrase your prompt or try a different approach.
    • Start with Your Own Writing: My favorite tip: write “quick and dirty” yourself. AI should refine your voice, jokes, and tone—not the other way around. This keeps the final output uniquely yours.
    • For Learning to Code: Just try it yourself first. Pain is part of the process—it’s the only way to truly learn. Use AI only when you’ve been stuck for a while and tried several approaches on your own.

    Closing Thoughts

    AI is a great thing. It turns mundane tasks (like writing product descriptions) into something fun, fast, and efficient. If you remember that you are the person writing and AI is the tool helping you, the results can often be surprisingly good—sometimes even better than what you’d have done on your own.

    For me, AI lets me focus more on the creative side, the “me” part, instead of stressing over, “What word should I use again?” or, “How was this phrased before?” It’s like having a brainstorming partner who never runs out of ideas.

    What can I say? Do your own research. Try it out. Experiment with different tools like Claude, Gemini, or others. Find what fits your workflow, and don’t be afraid to adapt. And stay tuned—there’s a lot more where this came from. I’ll be testing new approaches to working with AI and sharing my experiences at least once a week.

    Did this post help you? Please let me know in the comments! I’d love to hear how you’re using AI or what questions you have. Have a good one!