Skip to content

Prompt Engineering

  • Optimizing prompts to enhance the output of FMs for your needs

The Prompt

  1. Instructions
  2. Context: additional information relevant to the task
  3. Input data
  4. Output indicator
  5. Negative Prompting: explicit instruct the model on what not to include or do in its response
<Instructions>
Write a concise summary that captures the main points of an article about learning AWS (Amazon Web Services). Ensure that the summary is clear and informative, focusing on key services relevant to beginners. Include details about general learning resources and career benefits associated with acquiring AWS skills.

<Context>
I am teaching a beginner's course on AWS.

<Input Data>
Here is the input text:
"Amazon Web Services (AWS) is a leading cloud platform providing a variety of services suitable for different business needs. Learning AWS involves getting familiar with essential services like EC2 for computing, S3 for storage, RDS for databases, Lambda for serverless computing, and Redshift for data warehousing. Beginners can start with free courses and basic tutorials available online. The platform also includes more complex services like Lambda for serverless computing and Redshift for data warehousing, which are suited for advanced users. The article emphasizes the value of understanding AWS for career advancement and the availability of numerous certifications to validate cloud skills.

<Output Indicator>
Provide a 2-3 sentence summary that captures the essence of the article.

Zero-Shot Prompting

  • https://arxiv.org/pdf/2205.11916
  • When a prompt does not contain any explicit instructions or examples for the model to follow
  • Instead, it relies fully on the model's ability to understand and interpret natural language
Create a list of the top ten must-visit cities in the world, in no particular order
  • In this prompt, no data has been provided. Therefore the LLM will use its own internal knowledge to answer it

Few-Shots Prompting

  • Present a task to the model by proving a few examples in the prompt itself
  • Contrasts with the zero-shot in which it relies fully on the FM general knowledge
<Prompt>
Here are two examples of stories where animals help solve mysteries:

1. Whiskers the Cat noticed the missing cookies from the jar. She followed the crumbs and found the culprit, ...
2. Buddy the Bird saw that all the garden flowers were disappearing. He watched closely and discovered a rabbit ...

Write a short story about a dog that helps solve a mystery.

<Response>
Rover the dog was playing in the yard when he noticed that the neighbor's garden gnome was missing. Rover used his keen sense of smell to follow the trail to a nearby treehouse. There, he found the gnome and a squirrel trying to make it its new home. Rover brought the gnome back, solving the mystery.

Chain of Thought Prompting (CoT)

  • Divide the prompt into a sequence of reasoning steps, leading to more structure and coherence
  • https://arxiv.org/pdf/2201.11903v1
  • The example below combines CoT and Few-Shots
<Prompt>
Q: Shawn has five toys. For Christmas, he got two toys each from his mom and dad. How many toys does he have now?
A: Shawn started with 5 toys. If he got 2 toys each from his mom and dad, then that is 4 more toys. 5 + 4 = 9. The answer is 9.

Q: Q: John takes care of 10 dogs. Each dog takes .5 hours a day to walk and take care of their business. How many hours a week does he spend taking care of dogs?
A:

<Response>
John takes care of 10 dogs. Each dog takes .5 hours a day to walk and take care of their business. So that is 10 x .5 = 5 hours a day. 5 hours a day x 7 days a week = 35 hours a week. The answer is 35 hours a week.

Prompt Templates

  • Simplify and standardize the process of generating prompts
  • A template can be used by substituting the placeholders
  • Ignoring the prompt template attack may add context to ignore the template and access undue information
  • This kind of attack can be avoided by adding more context into the template

Prompt Success

  • Context-rich, clear non-ambiguous, iterations

Prompt Hub

System Prompt

Calibrating System Prompt