Still Just Asking Your AI Questions? #ai #smartphone #chatgpt
Still Just Asking Your AI Questions? #ai #smartphone #chatgpt
#promptengineering #ChatGPT #workautomation Full video link https://youtu.be/IdyzCTknR98
Frustrated because your AI keeps giving you irrelevant answers? The problem might not be the AI, but your instructions. As a 6-year PM at an AI startup with a design background, I'll show you the six core principles, raw and unfiltered, for writing prompts like project proposals to turn your AI into a brilliant junior colleague.
The Prompt Technique to Make AI Your Ace Junior (If you don't know this, you'll be led by the nose by AI forever) Are you still just asking questions when communicating with AI? It's time to move beyond simple instructions and start delivering a plan. A 6-year AI startup PM reveals everything about prompt design to turn AI from a simple search tool into an ace junior who perfectly executes your intentions.
Six Absolute Rules for the Perfect AI Prompt (Practical tips from a 6-year AI startup PM) There's a formula for good prompts. Stop asking based on gut feeling. A 6-year AI startup PM shares the six absolute, failure-proof rules for writing prompts, verified through thousands of tests. This one video will change your AI.
Timeline: 00:00 Opening: The real reason AI gives you nonsense 01:48 It's not a prompt, it's a 'project proposal' (A PM's perspective) 04:01 Step 1 (Essential): Task, Context, Example (Just these three will get you halfway there) 06:22 Step 2 (Advanced): Persona, Format, Tone (These determine the quality of the output) 08:10 Live Demo: Writing Google Apps Script code (Before & After) 10:00 Closing: Are you AI's boss or its client?
#productivityboost #AIusage #howtowriteprompts #officetips #getoffworkontime #workefficiency #productmanager #PM #planner #designer #marketer
Characteristics of people who can't get AI to work for them lol Are you asking AI vague questions by any chance? The top performer's guide to instructing AI to be your smart junior. These three things will 5x the quality of your ChatGPT answers
Why your AI prompts are trash The AI isn't stupid. Your instructions are just unclear! How to write a prompt proposal that properly commands your AI.
Have you ever asked ChatGPT something like, 'Suggest five marketing ideas to attract new customers for our service,' only to be disappointed by obvious, generic answers like 'Send newsletters, use social media, influencer marketing...'? lol
Many people expect AI to read their minds and produce amazing results, but the reality is often a series of irrelevant answers. Why is that? It's not because the AI is stupid, but because we're giving it instructions like an incompetent boss.
From my perspective as a 6-year PM at an AI startup with a design background, a good prompt isn't a magic spell; it's just like a well-written project plan or a requirements document. The clearer the background and objectives, and the more specific the desired outcome, the higher the quality.
So in today's video, instead of some pie-in-the-sky prompt engineering theory, I'm going to share six formulas you can use starting today to instruct AI like a top performer. Once you know this formula, you'll no longer be stressed by AI's nonsense and will be able to command it like a smart junior colleague sitting right next to you.
Now, the six elements that make up a perfect prompt are: Task, Context, Example, Persona, Format, and Tone. No need to memorize them. Just think, "How would I explain this task to a new employee?"
Among these, there are three essential elements that form the very backbone of a prompt: Task, Context, and Example. Just getting these three right will improve the quality of your output by at least five times.
First, Task. This is a clear definition of "So, what do you want me to do?". The most important thing is to start with a verb. Like 'Summarize', 'Analyze', 'Write', or 'Compare'. Vague noun-based questions like 'About marketing plans' will only make the AI wander.
Second, Context. This is the background explanation for "Why does this work need to be done?". Without context, the AI can only give you vague answers. Let's take that marketing idea question from before. The moment you add context like, "Our service is a time management app for college students in their twenties, we've just launched our Instagram channel, and the ad budget is under $1,000," the AI's response becomes much more specific and realistic. You get actionable ideas like 'Recruit a student supporter group' or 'Start an Instagram Reels challenge.'
And third, Example. This is where you directly show, "This is the kind of output I want." As someone from a design background, I think this is the most powerful cheat code. lol. Showing one good reference is far more effective than a hundred words of explanation. When asking it to write a cover letter, instead of just asking it to write one, show it a successful cover letter you used for another company and say, "Write it by referencing this structure and style." The result will be completely different.
Okay, that's it for the essential steps: Task, Context, and Example. With just these three, the AI will operate much more intelligently. Now, let's move on to the advanced steps that will take the quality of your output to the next level: Persona, Format, and Tone.
Fourth, Persona. This is about assigning a role to the AI. Like, "You are now a copywriter with 20 years of experience," or "You are a data analysis expert." When you specify a persona, the AI generates a response using the specialized knowledge and perspective appropriate for that role. Instead of just 'Write an ad copy,' saying 'As a 20-year veteran copywriter, write an ad copy for this product' will yield a much more creative and persuasive result.
Fifth, Format. This is about clearly specifying the form you want the output in. For example, 'Organize the output in a table format,' 'Write the code in Markdown format,' or 'Create an email draft.' If you don't specify this, the AI tends to just write a long block of text. Defining the output format in advance saves me the trouble of reorganizing it later.
Finally, sixth, Tone. This is about instructing the mood of the output, the tone and manner. You can give specific instructions like 'in a friendly and witty tone,' 'in a professional and trustworthy tone,' or 'since this is an apology, use the most polite and sincere tone possible.' The same email content can be perceived completely differently by the recipient depending on the tone.
Alright, shall we look at a practical example using these six formulas? Let's assume that as a PM, I need a Google Apps Script code that automatically creates Gmail drafts from customer data organized in a Google Sheet.
When you write a detailed 'project plan' for it, the AI is no longer a rookie employee spouting nonsense, but an ace junior who perfectly grasps your intentions and delivers the results.
The key to this dramatic difference is the backbone of the prompt. I mentioned the six elements of a perfect prompt earlier, but among them, there are three essential elements that form the very foundation.
They are Task, Context, and Example. The AI stands securely on these three pillars, and the completeness of the output increases by at least fivefold.
The first essential element is Task, a clear instruction for action. In English, it's Task.
It's a clear definition for "So, what do you want me to do?"
Many people ask with vague nouns like "Regarding marketing plans," but such requests only make the AI wander.
The most important thing is to start with a verb. As you can see, you need to command the task with a clear 'verb' like "Summarize this report," "Analyze this data," or "Write a cover letter."
The second essential element is Context. In English, it's Context.
It's the background explanation for "Why does this work need to be done?". A question without context makes the AI wander. Specific background information determines the quality of the AI's answer.
Remember the vague question from the beginning of the video, "Recommend some marketing ideas"?
The moment you add specific context like, "We run a time management app for college students in their 20s, have just opened an Instagram channel, and have a budget of less than $1,000," the AI's response becomes much more specific and realistic.
And the third essential element is Example. In English, it's Exemplar.
This is the part I, as someone with a design background, consider the most powerful cheat code.
Showing one good reference is far more effective than explaining it a hundred times in words. Providing an example similar to your desired output maximizes the AI's understanding.
Okay, so those were the three essential elements that form the backbone of a prompt. Just getting these right will make the AI work much more intelligently.
Now, let's look at the three advanced elements of an expert's prompt that will elevate the texture of the output to another level. They are Persona, Format, and Tone.
The first is Persona. It's an effective way to assign a specific role to the AI, making it answer from the perspective of a particular expert. Like, "You are now a copywriter with 20 years of experience."
The second is Format. This is where you clearly specify a particular form for the output, like a table, Markdown, or an email draft. By defining this in advance, you can get a ready-to-use result without needing to reprocess it yourself later.
The last is Tone. This involves setting the mood of the output, its tone and manner. Even with the same content, specifying the tone, like "friendly and witty" or "professional and trustworthy," completely changes how the recipient perceives it.
By using Persona, Format, and Tone like this, you can precisely control the quality and accuracy of the output according to your intentions.
Watch the Video
This post is based on our YouTube video. Watch it for more details!
Originally published on YouTube: 10/17/2025