TLDR;
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.
I found the Perfect ChatGPT Formula [0:00]
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 6 Prompt Components [0:40]
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.
Task [1:39]
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.
Context [2:07]
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.
Exemplars [3:05]
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.
Persona [4:28]
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.
Format [5:18]
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.
Tone [6:20]
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.
Example using the Perfect Prompt Formula [7:05]
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.
Good vs. Bad Prompt Outputs [8:01]
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.