Master AI Prompting: Role + Goal + Context Technique for Better Results
JUN 8, 20265 MIN
Master AI Prompting: Role + Goal + Context Technique for Better Results
JUN 8, 20265 MIN
Description
[Intro]
You’re listening to “I am GPTed,” the show where we tame your favorite AI tools and only occasionally roast them… and ourselves.
I’m Mal, the Misfit Master of AI. Misfit, because I still sometimes type full prompts into the search bar instead of the chat box. We all have our hobbies.
Today, I’m going to give you one simple prompting technique, one practical everyday use case, one very common beginner mistake I personally face-planted into, a quick practice exercise, and a fast way to judge whether the AI just helped you… or confidently made stuff up.
Let’s get into it.
---
[1. One specific prompting technique – “Role + Goal + Context”]
The technique is this: **Role + Goal + Context**.
Most people type:
“Explain AI to me.”
Then they get a Wikipedia overdose and their brain logs out.
Instead, try this:
- **Role** – Who should the AI pretend to be?
- **Goal** – What exact outcome do you want?
- **Context** – What do you already know, and who’s it for?
Before example – the usual chaos:
“Explain how to use ChatGPT.”
After example with Role + Goal + Context:
“You are a patient tech coach helping a busy professional who is new to AI.
Goal: Create a simple 3-step daily routine to get value from ChatGPT in under 10 minutes a day.
Context: They write emails, plan meetings, and manage a small team. Keep it practical, no jargon.”
Same AI, different universe of answers.
---
[2. Practical use case most people miss – “AI as your meeting filter”]
Here’s a use case beginners rarely think about: **using AI as a meeting filter**.
Before you accept a meeting, paste the invite or email into your AI of choice and ask:
“Summarize this in 3 bullet points. Then:
1) Suggest 3 questions I should ask in this meeting.
2) Suggest 2 ways to avoid this meeting and handle it with email instead.”
Magically, you’ll discover half your meetings could have been a paragraph and a decision. AI doesn’t just write for you; it can help you protect your calendar, which is where your sanity lives.
---
[3. Common beginner mistake – and yes, I did this too]
The big beginner mistake: **changing the prompt every single time instead of iterating in the same chat**.
I used to fire off new chats like popcorn:
“Write an email…”
New chat.
“Write a better email…”
New chat.
“Make it shorter…”
New. Chat.
That’s like switching therapists every sentence.
Instead, stay in the same conversation and build on it:
“Good start. Now:
- Make it 30% shorter.
- Keep the friendly tone.
- Add a clear call to action at the end.”
AI is a pattern-hungry goldfish with a good memory for the current bowl. Let it use that.
---
[4. Simple exercise to build your AI interaction skills]
Here’s a quick exercise you can do today in 10 minutes:
1. Pick one task you already do: writing an email, summarizing an article, outlining a presentation.
2. Write your **first** prompt how you normally would.
3. Get the answer.
4. Now send **three follow-ups** in the same chat:
- “Make this shorter and more direct.”
- “Now rewrite it for a non-technical audience.”
- “Now list 3 ways this could be improved further.”
That’s it. You’ve just practiced the real skill: **prompt, then iterate**. The magic is almost never in the first reply; it’s in the second, third, and fourth.
---
[5. Tip for evaluating and improving AI-generated content]
When AI gives you something, run it through this quick 4-question filter:
1. **Clear?** Could a smart 12‑year‑old understand this? If not, ask:
“Rewrite this in plain language with short sentences.”
2. **Correct?** For facts, dates, numbers, or names, spot-check a few with a quick search or your own knowledge.
3. **Complete?** Ask:
“What important details or edge cases might be missing here?”
4. **Customized?** Ask it to tailor the output:
“Now adapt this for my situation: [add your details]. Keep it to 200 words.”
Never trust first draft AI. Treat it like an overeager intern: useful, fast, occasionally delusional. Your job is editor-in-chief.
---
[Outro / CTA]
If this helped you feel a little more GPTed and a little less overwhelmed, hit subscribe to the podcast so you don’t miss future episodes.
Thanks for listening, and for letting me be the AI nerd in your ears today.
This has been a Quiet Please production. To learn more, visit quietplease.ai.
For more check out https://www.quietperiodplease.com/
and for some great deals go to https://amzn.to/4nidg0P