[Intro music fades in, then under]

This is “I Am GPTed,” I’m your host Mal – the Misfit Master of AI, here to help you talk to robots without feeling like you need a PhD… or a ring light.

Today we’re going to fix one of the biggest problems people have with tools like ChatGPT, Claude, Gemini, Grok, all of them: you type something in, it spits something out, and you go, “That’s… not what I meant at all.”

So let’s walk through one simple prompting technique, a sneaky use case you probably haven’t tried, a mistake you are absolutely making, a quick practice exercise, and a way to judge whether the AI just gave you gold… or recycling.

---

First up: **the prompting technique** – I call it *“Do it, then fix it.”*

Instead of asking for perfection in one shot, you ask the AI to give you a rough draft, then immediately tell it how to improve it.

Before:
“Write a professional email to my boss about needing tomorrow off.”
You get: stiff, generic, possibly written by a 1998 fax machine.

After:
“Write a casual but respectful email to my boss asking for tomorrow off.
Step 1: Give me a short rough draft.
Step 2: I’ll give feedback.
Step 3: Rewrite it based on my feedback.”

Then you say:
“Too formal, shorter, and mention I’ve already cleared my tasks.”
Now the AI rewrites with your preferences baked in.
Same model, same brain, wildly better output because you *iterated* instead of begging for magic.

---

Practical use case you probably haven’t tried: **decision comparison.**

Instead of “Which laptop should I buy?”, try:
“I’m choosing between these three laptops: [list].
Make a table comparing them for: price, battery, weight, and what matters most for someone who travels a lot and does video calls all day.
Then recommend one and explain why in plain English.”

Boom: instant, transparent pros and cons. It’s like having that one nerdy friend who loves specs, without having to buy them pizza.

---

Common beginner mistake: **one-and-done prompts.**

You fire off a vague question, get a vague answer, sigh, and decide AI is overrated.
I did this for weeks. My early prompts were basically:
“Explain AI.”
That’s not a prompt, that’s a cry for help.

Fix it by treating AI like a *conversation*, not a vending machine.
If the first answer is off, follow up:
“Less technical.”
“Give an example from everyday life.”
“Now explain like I’m 12.”
Every follow-up is a free upgrade. Use it.

---

Simple exercise to build your AI muscles: **the “three passes” drill.**

Pick one small task – say, writing a message to a client, or planning a workout.

Pass 1: “Draft a quick message to my client explaining I’ll deliver their report on Friday instead of Thursday. Keep it friendly and confident.”
Pass 2: “Now shorten it by 30% and make it a bit more casual.”
Pass 3: “Now give me one alternative version with a slightly more formal tone.”

Read all three. Notice which one *feels* right. You’re training two things: giving clearer instructions, and recognizing what “good” looks like for you.

---

Tip for evaluating and improving AI-generated content: **check it like you’d check a co-worker’s work on their first week.**

Ask yourself five questions:
1. Is anything obviously wrong or made up?
2. Is the tone right for the person who’ll read this?
3. Is anything missing that I *know* should be there?
4. Is anything extra that I don’t need?
5. Can I ask the AI to fix this in one line?

Then give it a punchy follow-up:
“Great start. Now:
- simplify the language,
- remove any fluff,
- and add one...

[Intro music fades in, then under]

This is “I Am GPTed,” and I’m Mal, your Misfit Master of AI — the only AI guide who still sometimes types “Chapt GPT” by accident and just rolls with it.

Today I’m going to show you one simple prompting move that makes your AI answers *way* better, a sneaky use case you probably haven’t tried, a mistake I used to make constantly, a quick practice exercise, and a dead‑simple way to judge if the AI just handed you gold…or glitter.

Let’s get into it.

---

So, the one prompting technique I want you to steal today is what I call **“Role + Result.”**

Two parts:
1. Tell the AI *who* it is.
2. Tell it exactly *what* you want back.

Here’s the lazy way most people – including past-me – do it:

> “Write me an email asking for a deadline extension.”

You’ll get something like:
> “Dear Sir or Madam, I humbly request a brief extension…”
Polite. Useless. Feels like a Victorian ghost wrote it.

Now the **Role + Result** version:

> “You are a friendly but professional project manager who writes clear, concise emails. Write a 120-word email to my manager asking for a 2-day deadline extension. Use everyday language, no fluff, and include one brief reason and one reassurance I’ll still deliver quality.”

Same task, totally different output:
Shorter, sounds like a human, and you don’t accidentally sound like a nervous intern from 1892.

Anytime you open an AI:
- Start with: “You are a [specific role]…”
- End with: “Give me [format, length, style].”

That’s it. Role + Result. Tattoo it on your prompt brain.

---

Now, a **practical use case** you might not be using: **turn the AI into your personal “thinking partner” for decisions.**

Not big life decisions, we’re not doing “Should I move to Bali?”
I mean everyday stuff like: “How should I structure my week so I don’t drown?”

Try this:

> “You are a productivity coach who works with overwhelmed beginners. Here is what my week looks like and what I need to get done: [paste your chaos]. Suggest a simple weekly schedule in plain language, with 3 priorities per day, and no more than 2 hours of meetings daily. Then summarize it in a bullet list I can paste into my calendar.”

Most people only ask AI to **write** things.
Use it to **think with you**. That’s where it quietly becomes absurdly useful.

---

Let’s talk about a **common beginner mistake** — my signature move when I started:

I used to type **massive, vague prompts** and then blame the AI.

Stuff like:
> “Help me with my business, marketing, and content strategy.”

That’s not a prompt; that’s a cry for help.

Here’s how to fix it:
- One clear goal per prompt.
- One clear audience.
- One clear output.

So instead of the monstrosity, you say:
> “You are a marketing coach for solo freelancers. I’m a web designer targeting small local businesses. List 5 simple content ideas I can post on LinkedIn this week to attract those clients. Keep each idea to one sentence.”

Specific in, specific out.
If your prompt could double as a therapy session, it’s too vague.

---

A **simple exercise** to build your AI skills this week:

Pick **one tiny task** you do often — emails, lesson plans, meeting notes, whatever.

1. Ask AI: “You are my assistant. Rewrite this to be clearer and shorter: [paste your thing].”
2. Then reply: “Now give me a second version that is more casual and a third version that is more formal.”
3. Compare the three, pick your favorite, tweak it.

Do that once a day for a week.
You’ll learn:
- How to ask for different tones.
- What you actually like.
- How...

[Intro music fades in, then under]

Hey, it’s Mal – the Misfit Master of AI – and you’re listening to “I Am GPTed,” the show where we turn confusing AI nonsense into… slightly less confusing AI nonsense you can actually use.

Today I’m going to give you one prompting technique, one sneaky use case, one painfully common mistake, one tiny practice exercise, and one quick way to fix AI’s worst ideas. All in about the time it takes your laptop to crash mid‑Zoom.

Let’s start with a **single prompting technique** that instantly upgrades your results:

**Give the AI a role, a goal, and a format.**

Most people just type:
“Help me write a better CV.”

That’s the “talking to a brick wall” prompt.

Try this instead:

“Act as a **recruiter for marketing roles** at mid‑size companies.
Your **goal** is to make my CV clearer and more results‑focused.
**Format** your answer in three sections: 1) What to remove, 2) What to rewrite, 3) One example bullet point for me to copy.”

Same topic. Completely different level of answer.

Before:
“Make my CV better.”
You get generic fluff.

After:
Role + Goal + Format.
You get targeted feedback, clear steps, and something you can paste straight into your doc. Magic. Boring, practical magic.

Alright, **one practical use case** you probably haven’t tried:
Use AI as your **“meeting distiller”** – even if no one writes proper notes. Which, let’s be honest, they don’t.

Right after a chaotic meeting, type:

“I’m going to brain‑dump messy notes from a meeting.
1) Turn them into: decisions, open questions, and action items with owners.
2) Keep it under 250 words.
3) Write it like a clear, friendly project manager.”

Then paste your messy bullets:

“Spoke about launch date, maybe mid‑March… Jess worried about support load… need pricing confirmed by finance… I’m supposed to draft FAQ…”

The AI turns that chaos into something you can drop into email or Slack and look weirdly competent.

Now, **one common mistake beginners make** – which I absolutely made:
Changing tools instead of changing prompts.

“I tried ChatGPT, it sucked. Claude was mid. Gemini didn’t ‘get’ me. Grok was… Grok.”
Yeah. I did the AI world tour too.

In reality, I was just giving garbage prompts:

“Explain AI.”
“Help with marketing.”
“Write content.”

That’s not a prompt, that’s a cry for help.

The fix:
Before you hit enter, ask:
“Would a normal human know what I want from this sentence?”
If not, add context: who you are, who it’s for, the style you want, and how you’ll use it.

Let’s do a **simple exercise** to build your AI interaction skills. This takes five minutes:

1. Pick one small task: “Write an email asking for a deadline extension.”
2. First prompt: “Write an email asking for a deadline extension. Keep it polite.”
3. Then do **two more rounds**:
- Round 2: “Make it sound like a stressed but responsible colleague. Add one light, human line.”
- Round 3: “Shorten it by 30%, keep it warm, and remove any cringe.”

Compare all three. You’ve just practiced **iterating**, which is 80% of using AI well. The win isn’t the first answer – it’s how fast you can shape the third.

Last thing: **how to evaluate and improve AI‑generated content** without needing a PhD or a spare weekend.

Use my three‑question gut check:

1. **Is it true?**
Anything that sounds too confident, too specific, or too convenient – verify it with a quick search or your own knowledge.

2. **Is it useful?**
If you can’t see the next physical action you’d take after reading it, ask:
“Turn this...

[Intro music fades in, then under]

This is “I Am GPTed,” and I’m Mal, the Misfit Master of AI – which mostly means I’ve broken every AI tool so you don’t have to.

Today I’m going to show you one simple prompting technique, a sneaky everyday use case, one big beginner mistake I personally face-planted on, a tiny practice exercise, and a fast way to judge whether the AI just gave you gold… or glitter.

Alright, let’s de-hype the robots.

---

First: **one prompting technique** that makes a huge difference.

It’s called **“Before/After + Constraints.”**
You tell the AI:

1) Who you are
2) What you want
3) How you want it shaped

Here’s the **before** prompt:

> “Write an email to my manager about working from home.”

Here’s the **after**:

> “You are my writing assistant.
> I’m a junior marketing specialist who usually writes too formally.
> Write a friendly, concise email to my manager asking to work from home on Fridays.
>
> Constraints:
> - 120 words or less
> - No buzzwords
> - Sound confident but not demanding
> - End with a clear question.”

Same human. Same goal. Completely different result.
Use this pattern for everything: “You are… I am… Do this… With these constraints…”

---

Next: **one practical use case** most beginners miss.

Use AI as your **“weekly work de-messifier.”**
Once a week, paste in:

- Your to‑do list
- A few recent emails
- Maybe meeting notes

Then ask:

> “Act as my prioritization assistant.
> I’m overwhelmed and have 10 hours of focused time this week.
> Group my tasks into: ‘Do this week’, ‘Delegate’, and ‘Delete’.
> Then suggest a simple weekly schedule.”

Suddenly the AI isn’t just writing poems about your dog; it’s helping you not cry into your calendar.

---

Now, **a common beginner mistake** – and yes, it’s mine too.

The mistake: **treating AI like a vending machine instead of a collaborator.**
I used to type something once, get a mediocre answer, and go, “Wow, this thing’s useless,” and close the tab.

What I should’ve done – and what you should do – is follow up:

- “Make that shorter.”
- “Give me 3 variations.”
- “Rewrite this so a 12‑year‑old understands it.”
- “Explain your reasoning step by step.”

Think of it like editing with a very patient, slightly nerdy coworker.
One prompt is the draft. The magic happens in the follow‑ups.

---

Let’s do a **simple exercise** to build your AI muscles.

Pick one small task from your real life:

- Draft a text to reschedule plans
- Explain your job to a 10‑year‑old
- Summarize a long email you’ve been avoiding

Step 1: Write your usual lazy prompt.
Step 2: Upgrade it using the formula:

> “You are [role].
> I am [who you are / context].
> Task: [what you want].
> Constraints: [length, tone, format].”

Step 3: Do **three follow‑ups**:
- “Make that clearer.”
- “Shorter.”
- “Now give me a bullet‑point version.”

That’s it. One tiny task, three iterations. You’ve just done more real prompt engineering than half of LinkedIn.

---

Finally, a **tip for evaluating and improving AI output.**

Use the **“3 C’s Check”: Clear, Correct, and Customized.

Ask yourself:

- **Clear** – Do I actually understand this? If not, ask:
“Rewrite this with simpler language and concrete examples.”

- **Correct** – Does anything look sketchy or outdated? If yes:
“List the parts of your answer you’re least confident about and why.”

-...

Welcome to “I Am GPTed,” the show where you learn to boss AI around… kindly.
I’m Mal, the Misfit Master of AI, here to help you get better answers from ChatGPT, Claude, Gemini, Grok, and whatever shiny model launches while you’re still figuring out the last one.

## One simple prompting technique

Today’s technique is: give the AI a role and a clear job.
Instead of saying, “Help me write a resume,” try: “You are a friendly career coach. Write a one-page resume for a junior marketer changing careers from retail. Use simple language and short bullet points.”

Before: “Write a resume.”
After: “You are a friendly career coach. Write a one-page resume for a junior marketer changing careers from retail. Use simple language, short bullets, and highlight customer-facing skills.”
Same human, same keyboard, wildly better output.

## A practical use case you’re missing

Here’s a use case most beginners skip: using AI as a weekly planning assistant.
You can paste in your messy to‑do list, your meetings, and your goals, then say, “Act as my no‑nonsense productivity coach. Turn this chaos into a realistic weekly schedule, by day, with time estimates, and flag anything I should probably say no to.”

Suddenly your half‑baked notes become a plan: priorities, time blocks, and even polite email wording to decline things.
It’s like having a project manager who never rolls their eyes… at least not out loud.

## A common beginner mistake

A classic mistake: treating AI like a vending machine instead of a collaborator.
People type one vague question, hate the answer, and declare, “This thing sucks,” as if they didn’t just ask it the equivalent of “Do my life please.”

Confession: Mal did this too.
The fix is to follow up.
Ask it to “Try again with simpler language,” or “Give me three shorter options,” or “Ask me three questions to make this better.”
Good AI use is less magic spell, more back‑and‑forth conversation.

## A simple practice exercise

Here’s a quick exercise to build your skills: the “three‑round refinement.”
Pick one small task: an email, a caption, a summary, a lesson plan.

Round 1: Ask for a basic version.
Round 2: Tell it what you liked and didn’t like, and ask for a revision.
Round 3: Ask it to shorten, clarify, or change the tone.

The goal isn’t perfection.
The goal is to get used to shaping the answer, instead of passively accepting the first thing it spits out.

## How to judge and improve AI output

When the AI gives you something, run it through three quick checks:
1) Is it accurate enough for the stakes?
2) Is it clear enough for a tired human to understand?
3) Does it sound like something you would actually say?

Then ask the model to help you fix it:
“Rewrite this in my voice: more casual, less corporate.”
“Highlight any claims I should fact‑check.”
“Give me a shorter version for someone who will skim.”
You’re not just getting answers; you’re co‑editing them.

That’s it for today’s episode of “I Am GPTed” with Mal, your slightly sarcastic tour guide through the AI jungle.
Make sure you subscribe to the podcast so you don’t miss future episodes.
Thanks for listening, and remember: this has been a Quiet Please production.
You can learn more at quietplease.ai.

For more check out https://www.quietperiodplease.com/

and for some great deals go to https://amzn.to/4nidg0P

This content was created in partnership and with the help of Artificial Intelligence AI

# I Am GPTed - Episode Script

**[INTRO MUSIC: Upbeat, slightly irreverent tech vibe fades under]**

**MAL:**
Hey, I'm Mal, your Misfit Master of AI, and welcome to "I Am GPTed"—the show where we make artificial intelligence actually useful instead of just impressive at parties. Today, we're talking about the one prompting trick that'll make your AI actually listen to you like you're paying it.

**[MUSIC FADES]**

## The Game-Changing Technique: Role-Playing

So here's the thing. Most people treat AI like a vending machine. You drop in a question, and hope something edible comes out. But what if I told you there's a dead-simple way to completely transform what you get back?

It's called **role-playing**, and no, we're not getting you a cape.

Here's the before version—the sad version—the version I used for approximately six months like an absolute amateur:

**BEFORE:** "Write me a marketing email for my coffee shop."

You get something generic. Corporate. Boring. Like watching paint dry while someone explains cryptocurrency.

**AFTER:** "You are a charismatic barista who genuinely loves connecting with customers. Write a marketing email for my coffee shop that sounds like you're texting a friend about your favorite hangout spot."

Suddenly? You get personality. Voice. Something that actually sounds like a human wrote it instead of a robot having an existential crisis.

The magic here is that you're not just asking the AI to do something. You're giving it permission to adopt a perspective. It's like the difference between asking a friend "what should I say?" versus "what would your grandma say about this?"

## Real-World Gold: Meal Planning for Your Brain

But here's where this gets genuinely useful. Let me give you something most people miss entirely.

You can use this exact same trick for meal planning. I know, thrilling. But stick with me.

Ask your AI: "You're a nutritionist who specializes in meals for people who work 10-hour days and have zero energy to think. Give me five meal prep ideas for this week." Suddenly you get practical suggestions that account for actual human exhaustion, not just optimal macros.

That's prompting working for your *life*, not just your LinkedIn posts.

## The Rookie Mistake (I Made This)

Here's the confession: I spent weeks frustrated with AI because I was too vague. I'd ask Claude something like "help me understand marketing" and get back a dissertation. I needed a thesis, not a textbook.

The fix? **Specificity is free.** Tell it your experience level. Tell it your exact goal. Tell it you want it in three paragraphs, not War and Peace.

Beginners think being specific limits creativity. It doesn't. It focuses it. It's like the difference between "draw something" and "draw a cat wearing sunglasses on a skateboard." The second one is better, obviously.

## Your Practice Exercise

Here's what you're doing this week: Take something you actually need—a cover letter, a product description, a complaint email you're too angry to write yourself—and try three different role-playing prompts. Compare the results. You'll feel the difference immediately.

## The Quality Check

After your AI generates something, ask yourself: Does this sound like how I actually talk? Would I send this to someone who matters? If the answer's no, give the AI feedback. "That's too formal" or "make it snarkier" or "this reads like a robot's diary."

AI improves with direction, just like everyone else.

**[MUSIC BUILDS]**

**MAL:**
Thanks for hanging out with me today. If this actually helped you sound less like a corporate alien in your emails, please subscribe wherever you're listening.

This has been "I Am GPTed"—a Quiet...

# I Am GPTed: The Art of Asking Better Questions

**[INTRO MUSIC: Upbeat, slightly quirky tech soundtrack fades in]**

**MAL:** Hey everyone, it's Mal—your friendly neighborhood AI enthusiast who still hasn't figured out how to use Siri correctly. Welcome back to "I Am GPTed," where we prove that you don't need to be a computer scientist to get computers to do awesome stuff for you.

Today, we're tackling something that'll genuinely change how you interact with AI. We're talking about **role-playing prompts**—and no, this isn't about pretending you're a wizard. Though honestly, if that gets you better results, go for it.

**[TRANSITION SOUND: Quick notification ding]**

## The Game-Changer: Role-Playing Prompts

Here's the thing about AI: it's like talking to the world's most knowledgeable person who's also incredibly literal. If you ask vaguely, you get vague answers. If you ask like you're talking to a specific expert? Magic happens.

**Before I knew this trick:**
"Explain machine learning."

**After I got smart about it:**
"You're a seasoned data scientist explaining machine learning to someone at a dinner party. Keep it conversational, skip the math, and use one really good analogy."

Suddenly, my AI doesn't sound like a Wikipedia article. It sounds like an actual human who knows their stuff.

## Where This Actually Matters in Real Life

Let's say you're writing performance reviews for your team—something most managers avoid like root canals. Instead of staring at a blank screen, try this: "You're an empathetic HR professional who's seen thousands of reviews. Help me write feedback that's honest, specific, and actually motivates improvement."

Boom. Different output entirely.

**[TRANSITION: Brief pause]**

## The Mistake I Made (And You Probably Will Too)

Here's me being vulnerable: I used to treat AI like a magic 8-ball. Ask a question, get an answer, done. Then I'd complain when it was useless.

The beginner mistake? **Assuming the first response is final.** It's not. AI outputs are like rough drafts. They need refinement, pushback, and iteration. You're not being "difficult" by asking follow-up questions—you're actually using the tool correctly.

Start viewing yourself as a collaborator, not a customer. Ask for specifics. Ask why. Ask again differently.

## Your Practice Exercise (Yes, Really Do This)

Spend ten minutes right now:

1. Pick something you actually need help with—not a test. A real task.
2. Write one prompt the "lazy way"
3. Write the same prompt with a specific role: "Act as [specific expert]. Keep the tone [specific style]. The output format should be [specific format]."
4. Compare the results

You'll see the difference immediately. Then you'll feel smarter. Then you'll wonder why nobody explains this stuff in plain English from the start.

## Making Sense of What You Get Back

Here's my golden rule: **AI content needs an editor.** Always. Check for accuracy, tone, and whether it actually solves your problem. Does it sound like you? Probably not yet. Does it have useful bones? Hopefully.

Copy-paste is for people who haven't thought about what they're doing.

**[OUTRO MUSIC BEGINS TO SWELL]**

**MAL:** That's what we've got for you this week on "I Am GPTed." Remember to subscribe so you don't miss future episodes where we figure out AI together—mistakes and all.

Thanks for listening, everyone.

**Do this:** Head over to **quiet please dot ai** to learn more and to see if there's something actually useful waiting for you there.

This has been a Quiet Please production.

Now go forth and prompt responsibly.

**[MUSIC FADES]**

For more check out Show more...