Master AI Prompting: Unlock Powerful Results with These Expert Techniques

DEC 15, 20255 MIN
I am GPTed - what you need to know about Chat GPT, Bard, Llama, and Artificial Intelligence

Master AI Prompting: Unlock Powerful Results with These Expert Techniques

DEC 15, 20255 MIN

Description

[Intro music fades in, then under]<br /><br />Hey, it’s Mal – the Misfit Master of AI – and this is “I Am GPTed,” the show where we turn buzzword soup into something you can actually use… like lunch. A weird, digital lunch.<br /><br />Today I’m giving you one simple prompting technique, a sneaky real‑life use case, a mistake I personally keep making, a quick practice exercise, and a fast way to clean up the AI’s mess before you hit send.<br /><br />Let’s get to it.<br /><br />---<br /><br />So, one prompting technique that instantly improves your results: **role plus format plus constraints**.<br /><br />Translation: tell the AI **who** to be, **what shape** you want the answer in, and **the rules** it has to follow.<br /><br />Here’s the lazy, “before” version:<br /><br />> “Explain blockchain.”<br /><br />Every model on earth will now send you a 700‑word Wikipedia tribute.<br /><br />Here’s the upgraded “after” version:<br /><br />> “You are a patient high‑school teacher. Explain blockchain to a 15‑year‑old who hates math. Use a real‑world money analogy, keep it under 150 words, and end with one sentence: ‘If you remember one thing, remember this: …’”<br /><br />Same topic, totally different vibe. You’ve told it:<br />- Role: patient high‑school teacher <br />- Format: short explanation plus one final sentence <br />- Constraints: teen, hates math, real‑world analogy, 150 words <br /><br />You can do this in ChatGPT, Claude, Gemini, Grok – they all respond better when you stop mumbling and actually give them a job description.<br /><br />---<br /><br />Now, a practical use case beginners usually don’t think about: **being your “second brain” for boring recurring messages.**<br /><br />Not presentations. Not novels. I’m talking about those awkward, repetitive things:<br />- “Sorry, I’m declining this meeting but still trying to sound like a team player.”<br />- “Following up without sounding desperate.”<br />- “Reminding the client they owe us money… politely.”<br /><br />Try this:<br /><br />> “You are my polite but assertive email assistant. Rewrite this follow‑up so it’s friendly, confident, and under 80 words. Keep my tone casual, no corporate clichés. Here’s my draft: [paste your mess].”<br /><br />You’re not asking the AI to be you. You’re asking it to be your **editor with social skills**.<br /><br />---<br /><br />Common beginner mistake time – and yes, I do this too: **asking once and accepting the first answer like it’s sacred scripture.**<br /><br />I still catch myself doing this:<br />I type a vague prompt, get a meh answer, sigh, and think, “Guess the AI just isn’t good at this.”<br /><br />No. I wasn’t good at asking.<br /><br />Instead of giving up, respond to the AI like this:<br /><br />> “This is too generic. Make it more specific to [my industry / my situation], add 3 concrete examples, and cut the fluff.”<br /><br />Or:<br /><br />> “You missed the part about [X]. Rewrite it and focus mainly on that.”<br /><br />Treat it like an **iterative conversation**, not a vending machine. If the first answer is bad, that’s not the ending – that’s the first draft.<br /><br />---<br /><br />Here’s a simple exercise to build your AI skills – takes five minutes:<br /><br />1. Pick a tiny task: summarize a page of text, write a short email, or plan a 3‑item shopping list dinner. <br />2. Write your **first** prompt quickly. Run it. <br />3. Now write **version two** of the prompt using role + format + constraints. Run that. <br />4. Compare the two answers and ask: <br /> - What did the better one have that the first prompt didn’t? <br /> - Did I say who it should be? What format I wanted? Any limits?<br /><br />Do this once a day for a week. You’ll accidentally become “that AI person” in your office, just from being slightly less vague than everyone else.<br /><br />---<br /><br />Finally, a tip for evaluating and improving AI‑generated content so you don’t copy‑paste yourself into disaster.<br /><br />Use this three‑question checklist:<br /><br />1. **True?** <br /> Ask the AI: <br /> > “List any claims in your answer that might be incorrect or need a source.” <br /> If it suddenly gets shy, you know where to double‑check.<br /><br />2. **Useful?** <br /> Ask: <br /> > “Rewrite this to be more practical for someone who is [your role] with [your constraint: no time, low budget, beginner, etc.]. Add concrete steps.” <br /><br />3. **Yours?** <br /> End with: <br /> > “Now simplify this into my voice: casual, clear, and direct. Short sentences. No buzzwords.” <br /> Then you still tweak it. AI gives you clay; you sculpt, even just a little.<br /><br />---<br /><br />That’s it for today’s dose of “I Am GPTed” with me, Mal, your misfit guide to making ChatGPT, Claude, Gemini, Grok, and the rest actually earn their electricity bill.<br /><br />Subscribe to the podcast so you don’t miss future episodes – or at least so I can pretend you didn’t.<br /><br />Thanks for listening.<br /><br />This has been a Quiet Please production. To learn more, head over to quietplease dot ai.<br /><br />For more check out <a href="https://www.quietperiodplease.com/" rel="noopener">https://www.quietperiodplease.com/</a><br /><br />and for some great deals go to <a href="https://amzn.to/4nidg0P" rel="noopener">https://amzn.to/4nidg0P</a><br /><br />This content was created in partnership and with the help of Artificial Intelligence AI