Brief Summary
This video explains a formula for writing effective prompts for AI models like ChatGPT and Google Bard. It breaks down the six key components of a good prompt: Task, Context, Exemplars, Persona, Format, and Tone, and explains the order of importance of these components. The video emphasizes the importance of providing enough relevant information to guide the AI model without overwhelming it.
- Task is the most important component, as it defines the desired outcome.
- Context provides the necessary background information for the AI model.
- Exemplars are examples that demonstrate the desired output format or style.
- Persona defines the role or perspective the AI model should adopt.
- Format specifies the desired output structure.
- Tone sets the desired style or attitude of the output.
The video introduces a formula designed to help users master prompting on AI platforms like ChatGPT and Google Bard. It addresses the common issue of inconsistent output quality from prompts, where some results are generic while others are highly specific and useful. The presenter shares insights gained from prompt engineering courses and practical application, distilling the knowledge into six building blocks for effective prompting.
The video outlines six key components of an effective prompt: Task, Context, Exemplars, Persona, Format, and Tone. It emphasizes that these components have a hierarchy of importance. Task and Context are most important. To illustrate, the video uses the example of requesting a 3-month training program, highlighting how context enriches the prompt and improves the output. Including relevant context and exemplars is important, while Persona, Format, and Tone are beneficial but not always necessary.
The video explains that the task component should always start with an action verb like "generate," "give," or "write." The task should clearly articulate the desired end goal, whether it's a simple request or a complex, multi-step process. For example, the task could be generating a three-month training program or analyzing user feedback, identifying key takeaways, and categorizing the feedback by team.
The video describes context as the trickiest component to get right because of the infinite amount of information you could include. To narrow it down, ask: What's the user's background? What does success look like? What environment are they in? Using the workout example, the context includes details like the user's weight, goals, time constraints, and frequency of gym visits. The key is to provide just enough information to constrain the possibilities and get a good result.
The video defines exemplars as examples included within a prompt to improve the output quality. A simple example involves rewriting a resume bullet point using a specific structure (I accomplish X by doing Y to measure Z). A more complex example involves using the STAR framework (Situation, Task, Action, Results) for interview preparation. For job descriptions, referencing an existing one can save time by ensuring the output follows the same formatting and uses professional HR language. Exemplars are not always necessary, but they can greatly improve the quality of the output.
The video explains that the persona component defines who you want the AI model to be. The pro tip is to think of someone you wish you had instant access to for the task you're facing. This could be a physical therapist for workout injuries, a recruiter for job seeking, or a product marketing manager for creative briefs. You can also name specific individuals, but the results are best when they're famous. Fictional characters can also work well as personas.
The video advises visualizing the desired end result to determine the appropriate format. For user feedback, a table with headers for feedback, responsible team, and priority might be ideal. Common formats include emails, bullet points, and code blocks. For professionals, paragraphs and markdown are particularly useful. When proofreading documents, specifying that changes should be bolded makes it easy to see what has been altered.
The video describes tone as setting the desired style or attitude of the output, such as casual, formal, witty, enthusiastic, or pessimistic. Since it's hard to recall specific adjectives and adverbs, the pro tip is to tell the AI model the feeling you're going for. For example, if writing an email to a new team, you can ask the AI model for tone keywords to sound confident and friendly without being cringey.
The video provides a comprehensive example prompt for writing an email from a senior product marketing manager at Apple to Tim Cook about the successful launch of the Apple car. The prompt includes the persona (senior product marketing manager at Apple), context (successful product launch with pre-order numbers), task (write an email to Tim Cook), and format (TLDR, project background, business results, thanking the teams). The tone is specified as clear, concise, confident, and friendly.
The video compares the output from the comprehensive prompt to that of a simpler prompt. The comprehensive prompt yields a much more detailed and usable result compared to the generic output from the simpler prompt.
Summarize any YouTube video in seconds
Get summaries like this one for any video, in your language, with the free Summ app.
Transcript
Full transcript of “Master the Perfect ChatGPT Prompt Formula (in just 8 minutes)!”. Click a timestamp to open the video at that moment. Need another video? Use the YouTube transcript generator.
0:00 I don't usually overhype myself but in this video we're going over the only formula you will ever need to master prompting on chat BT and Google bard so let's get started hey friends welcome back to channel if you're new here my name is Jeff I 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 since 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 first it's critical to not only know what the six components are task
0:45 context exemplars Persona format and tone but also know that there's an order of importance to these six components to 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 the 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 but if we just give Chachi PT the context nothing really happens put another way it's mandatory to have a task in your prompt it's important to include relevant context and exemplars and it's nice to have Persona format and tone when you think of writing your prompt go down this mental checklist so this formula will act as a constant reminder for you to include just enough relevant
1:32 information when writing prompts and as you'll see in this next part you do not need all six components in every prompt to have a good output now let's break down each building block with specific examples starting with the task the 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 it 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 the second component context is the trickiest to get right because technically there's an infinite amount of information you can give so I found asking myself these three
2:17 questions to be super helpful in coming up with just enough information to get a good result from Chachi BT first what's the user's background second what do 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 5 kg of muscle mass over the next 3 months I only have time to go to the gym twice a week and for 1 hour each session give me a 3month training program to follow could I have added more background information of course only prioritize the muscle groups that make me look good at Instagram but the key to staying productive with chat gbtm Bard is giving just enough information to constrain the endless possibilities by the way although this video is not sponsored it is supported by those of you you who subscribe to my paid positivity newsletter on Google workspace tips Link
3:03 in the description to learn more moving over to the exemplars component it's just a fancy way of saying examples basically all the research on large language models llms have shown that including examples within the prompt drastically improves the quality of the output starting with a simple example this is a py written bullet point from a resume we can now ask chat GPT to rewrite this bullet point using this structure I accomplish X by to measure y that resulted in Z which is actually best practice by the way so actually do this in your resume for example I lowered Hospital mortality rate by 10% by educating nurses in new protocols which translates to 200 lives saved per year here'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
3:49 weakness use the star answer framework situation task action and results here instead of using a full-blown interview answer as an example which would be Overkill the star framework acts as an example structure for chat gbt to follow last example let's say you need to write a job description you give some context around the opening and ask chat apt to reference an existing job description if I use this one I found on LinkedIn the output will follow the same formatting and use the same professional hre language saving me a bunch of time main takeaway here exemplars are not necessary for every prompt but including a relevant example or framework will greatly improve the quality of your output moving along the Persona component is basically who you want cha PT and bar to be and the pro tip here is
4:36 to think of someone you wish you had instant access to with the task you're facing if you injured yourself working out that person might be a physical therapist with experience helping athletes recover if you're a jobseeker that person might be a recruiter or Hing manager if you're working on a creative brief that person might be a senior product marketing manager who's great at storytelling Pro 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 by the way I just have to share this we have a team offsite with a superheroes theme so I asked Chach PT 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 format the pro tip here
5:22 is to literally close your eyes and visualize how exactly you want the end result to look like a million likes on my thir bomb Instagram photo damn it didn't work back to the user feedback example I don't want to read each sentence so I asked chachy BT to take all the feedback and output a table with three headers the original feedback the team responsible for following up and priority and now I can copy this directly and paste it into a Google sheet store by priority and filter by team other 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 and markdown for example I just received a lengthy industry report from my director first give me the three key takeaways then summarize based on topic use H2 as section headers
6:10 here is the report Pro tip whenever I use chash gbt to proofread any document I specify that all changes need to be bolded so I can easily see exactly what has been changed let's quickly go through the last component tone before we put all this together in one example the good news is tone is easy to understand use a casual or formal tone of voice give me a witty output uh show enthusiasm sound pessimistic the bad news is we're usually not very good at recalling the thousands of potential adjectives and adverbs at a moment's notice so here's a pro tip tell tra BT the feeling you're going for for 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 can you please
6:55 give me a list of five tone keywords I can include in a prompt for chbt 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 you are a senior product marketing manager at Apple Persona 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 context write an email to your boss Tim cookie sharing this positive news task and format the email should include a tldr tool 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
7:41 example structure use clear and concise language and write in a confident yet friendly tone tone note that if I had an existing email to reference I could delete the instructions around the structure and simply tell chbt the email should follow the exact same format as the one I will share below and paste the email from before by the way you can compare the output from this prompt to that of a simpler prompt I just launched a new product the Apple car I received 12,000 pre-orders please run an email to my boss with this update there's a pretty big difference in terms of how generic and usable the end result is now 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 check out my top five CH gbt productivity tips for work see you on the next video in the
8:26 meantime have a great one
