00:00I don't usually overhype myself, but in this video, we're going over the only formula you will ever need to master prompting on ChatGPT and Google Bard, so let's get started
00:09Hey friends, welcome back to the channel
00:11If you're new here, my name is Jeff
00:12I work full-time in tech, and if you're anything like me, a couple months ago, you know prompting is an important skill to learn, but you're not exactly sure why some prompts generate outputs that are super generic, while others give you precisely what you're looking for
00:26Since then, I've spent hundreds of hours taking prompt engineering courses and applying what I've learned in my daily life, and so in this video, I'm sharing these six building blocks that make up a good prompt, so that you can Use this formula to consistently generate high-quality outputs
00:41First, it's critical to not only know what the six components are: task, context, exemplars, persona, format, and tone, but also know that there's an order of importance to these six components
00:50To show you what I mean, let's use this simple example: "I'm a 70kg male, give me a 3-month training program." The first part is context, followed by the task
00:59The reason why the task is higher up in the formula hierarchy is if we just input the task without the context, there's still some sort of meaningful output
01:07But if we just give ChatGPT the context, nothing really happens
01:12Put another way, it's mandatory to have a task in your prompt
01:16It's important to include relevant context and exemplars, and it's nice to have persona, format, and tone
01:23When you think of writing your prompt, go down this mental checklist
01:26So, this formula will act as a constant reminder for you to include just enough relevant information when writing prompts
01:32And as you'll see in this next part, you do not need all six components in every prompt to have a good output
01:39Now, let's break down each building block with specific examples, starting with the task
01:42The rule of thumb is to always start the task sentence with an action verb: generate, give, write, analyze, etc., and clearly articulate what your end goal is
01:51It could be one simple task, like generating a three-month training program, or a complex three-step task, like analyzing hundreds of user feedback, sharing the top three takeaways and categorizing the feedback based on the team responsible for following off
02:07The second component, context, is the trickiest to get right because technically, there's an infinite amount of information you can give
02:13So, I found asking myself these three questions to be super helpful in coming up with just enough information to get a good result from ChatGPT
02:21First, what's the user's background? Second, what does success look like? And third, what environment are they in? Back to the workout example, we now have: I'm a 70kg male looking to put on 5kg of muscle mass over the next 3 months
02:35I only have time to go to the gym twice a week for 1 hour each session
02:38Give me a 3-month training program to follow
02:41Could I have added more background information? Of course
02:45Only prioritize the muscle groups that make me look good on Instagram
02:48But the key to staying productive with ChatGPT and Bard is giving just enough information to constrain the endless possibilities
02:55By the way, although this video is not sponsored, it is supported by those of you who subscribe to my paid positivity newsletter on Google Workspace tips
03:01Link in the description to learn more
03:03Moving over to the exemplars component, it's just a fancy way of saying examples
03:10Basically, all the research on large language models, LLMs, have shown that including examples within the prompt drastically improves the quality of the output
03:19Starting with a simple Example, this is a Python-written bullet point from a resume
03:23We can now ask ChatGPT to rewrite this bullet point using this structure: I accomplish X by doing Y to measure Z, which is actually best practice, by the way
03:32So actually do this in your resume
03:33For example, I lowered hospital mortality rate by 10% by educating nurses in new protocols, which translates to 200 lives saved per year
03:41Here's a slightly more complicated example for interview prep: Based on my own resume, write me an answer to the interview question, "What's your biggest weakness?" Use the STAR answer framework: Situation, Task, Action, and Results
03:52Here, instead of using a full-blown interview answer as an example, which would be overkill, the STAR framework
03:58acts as an example structure for ChatGPT to follow
04:04Last example, let's say you need to write a job description
04:05You give some context around the opening and ask ChatGPT to reference an existing job description
04:09If I use this one I found on LinkedIn, the output will follow the same formatting and use the same professional HR language, saving me a bunch of time
04:17Main takeaway here, exemplars are not necessary for every prompt, but including a relevant example or framework will greatly improve the quality of your output
04:29Moving along, the persona component is basically who you want ChatGPT and Bard to be, and the pro tip here is to think of someone you wish you had instant access to with the task you're facing
04:40If you injured yourself, working out that person might be a physical therapist with experience helping athletes recover
04:45If you're a job seeker, that person might be a recruiter or hiring manager
04:49If you're working on a creative brief, that person might be a senior product marketing manager who's great at storytelling
04:54Pro tip: you can also name specific individuals, but I found the results to be good only when they're famous enough, like Warren Buffett, Steve Jobs, Jeff Sue
05:04By the way, I just have to share this, we have a team offsite with a superhero theme, so I asked ChatGPT to draft an email from Batman, and it even included things like, "Please let Alfred know," and signed off as, "The Dark Knight." Um, so fictional characters work as well, and I'm actually going to Use this, the fifth component
05:19The pro tip here is to literally close your eyes and visualize how exactly you want the end result to look like
05:26A million likes on my third bomb Instagram photo
05:28Damn, it didn't work
05:30Back to the user feedback example
05:32I don't want to read each sentence, so I asked ChatGPT to take all the feedback and output a table with three headers: the original feedback, the team responsible for following up, and priority
05:43And now I can copy this directly and paste it into a Google sheet, sorted by priority and filtered by team
05:51Other common formats include emails, bullet points, and code blocks, but the one I found to be the most useful as a full-time working professional is paragraphs and markdown
05:58For example, I Just received a lengthy industry report from my director
06:02First, give me the three key takeaways
06:04Then, summarize based on topic
06:06Use H2 as section headers
06:11Here is the report
06:15Pro tip: Whenever I use ChatGPT to proofread any document, I specify that all changes need to be bolded so I can easily see exactly what has been changed
06:19Let's quickly go through the last component, tone, before we put all this together in one example
06:25The good news is, tone is easy to understand
06:27Use a casual or formal tone of voice
06:29Give me a witty output, uh, show enthusiasm, sound pessimistic
06:33The bad news is, we're usually not very good at recalling the thousands of potential adjectives and adverbs at a moment's notice
06:42So here's a pro tip: Tell ChatGPT the feeling
06:45For example, I'm writing an email to a team I haven't worked with before, and I want to be taken seriously without coming off as too stuck up and cringey
06:52Can you please give me a list of five tone keywords I can include in a prompt for ChatGPT? And look, now, in the actual prompt, I can say, "Use clear and concise language and write in a friendly yet confident tone." Putting all this together, let's look at this comprehensive prompt
07:08You are a senior product marketing manager at Apple
07:12Persona: And you have just unveiled the latest Apple product in collaboration with Tesla, the Apple car, and received 12,000 pre-orders, which is 200% higher than target
07:20Context: Write an email to your boss, Tim Cook, sharing this positive news
07:27task and format
07:34The email should include a TLDR (Too Long; Didn't Read) section, project background (why this product came into existence), business results section (quantifiable business metrics), and end with a section thanking the product and engineering teams
07:41Example structure: Use clear and concise language, and write in a confident yet friendly tone
07:46Tone note: that if I had an existing email to reference, I could delete the instructions around the structure and simply tell ChatGPT the email should follow the exact same format as the one I will share below, and paste the email from before
08:00By the way, you can compare the output from this prompt to that of a simpler prompt
08:03I just launched a new product, the Apple car
08:06I received 12,000 pre-orders
08:08Please run an email to my boss with this update
08:10There's a pretty big difference in terms of how generic and usable the end result is
08:13Now that you know the basics of prompting, my next video is going to take you from beginner to pro, so make sure you're subscribed for that
08:21Check out my top five ChatGPT productivity tips for work
08:25See you on the next video
08:25In the meantime, have a great one.