Importance of mastering prompting for generating high-quality outputs
Overview of the six building blocks of a good prompt
Six Components of a Good Prompt
Task
Always start with an action verb (e.g., generate, give, write, analyze)
Clearly articulate the end goal
Example: "Generate a three-month training program."
Context
Critical component, provides necessary background
Ask three questions for effective context:
What's the user's background?
What does success look like?
What environment are they in?
Example: "I'm a 70 kg 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 for 1 hour each session."
Exemplars
Examples to improve output quality
Can include well-structured frameworks or existing documents
Example: Rewriting resume bullet points using best practices (e.g., "I lowered hospital mortality rate by 10%...")
Not necessary for every prompt but beneficial when included.
Persona
Define who ChatGPT or Bard should emulate
Think of a person who could help with the task at hand (e.g., a physical therapist, recruiter, or product marketing manager)
Example: Asking ChatGPT to respond as if it were a famous person (e.g., "Draft an email from Batman.")
Format
Visualize the desired output format (e.g., table, bullet points, paragraphs)
Example: Requesting feedback to be organized in a table with specific headers
Common formats include emails, markdown, and code blocks.
Tone
Specify the tone of the output (e.g., casual, formal, witty)
Provide a feeling or keyword descriptors to guide the tone
Example: "Use clear and concise language in a friendly yet confident tone."
Comprehensive Prompt Example
Prompt:
"You are a senior product marketing manager at Apple, 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 expected. Write an email to your boss, Tim Cook, sharing this positive news. The email should include:
TLDR section
Project background
Business results section with quantifiable metrics
A thank you note to the product and engineering teams.
Use clear and concise language and write in a confident yet friendly tone."
Comparison:
Simpler prompt yields generic results, while a detailed prompt is much more useful.
Conclusion
Importance of understanding and applying the six components for effective prompting.
Upcoming videos will build on this knowledge to further improve skills.