Introduction

Based on White et al. (2023), this toolkit presents a categorized set of reusable “prompt patterns” to help you interact more effectively with ChatGPT. These patterns are structured techniques designed to solve common problems when prompting large language models (LLMs).

📦 Meta Language Creation

🎨 Translation

• Transformation: Change from one languange or context into another.

  “When I say X, I mean Y (or would like you to do Y)”

📦 Prompt Pattern Categories, Tools & Examples

🎨 Output Customization

• Persona: Assign a character or role.

  “Act as a security reviewer... Provide outputs that a security reviewer would regarding the code.”

  “From now on, act as a security reviewer. Pay close attention to the security details of any code that we look at. Provide outputs that a security reviewer would regarding the code.”

• Recipe: Step-by-step instructions.

  “I am trying to deploy an application to the cloud... Please provide a complete sequence of steps.”

  “Whenever you produce an output that has at least one step to take and the following properties (alternatively,always do this)”

  “Produce an executable artifact of type X that will automate these steps”

• Template: Fixed structure output.

  “Please preserve the formatting and overall template that I provide at https://myapi.com/NAME/profile/JOB”

  ““I am going to provide a template for your output. Everything in all caps is a placeholder. Any time that you generate text, try to fit it nto one of the placeholders that I list. Please preserve the formatting and overall template that I provide at https://myapi.com/NAME/profile/JOB”

  “I am going to provide a template for your output”

  “X is my placeholder for content”

  “Try to fit the output into one or more of the placeholders that I list”

  “Please preserve the formatting and overall template that I provide”

  “This is the template: PATTERN with PLACEHOLDERS”

  “Please convert this into a JSON array where each row becomes an object with two keys: "category" and "pattern". The output should be valid JSON syntax.”

• Visualization Generator: Textual input for tools like Graphviz or DALL·E.

  “Whenever I ask you to visualize something, create either a Graphviz Dot file or DALL-E prompt.”

• Output Automater: Generate scripts to automate steps.

  “Generate a Python script that can be run to automatically create the specified files.”

❌ Error Identification

• Fact Check List: Add facts to verify at the end.

  “Create a set of facts that the answer depends on that should be fact-checked.”

• Reflection: Explain why ChatGPT gave a certain answer.

  “Explain the reasoning and assumptions behind your selection of software frameworks...”

  “Whenever you generate an answer Explain the reasoning and assumptions behind your answer (Optional) ...so that I can improve my question”

  “When you provide an answer, please explain the reasoning and assumptions behind your selection of software frameworks. If possible, use specific examples or evidence with associated code samples to support your answer of why the framework is the best selection for the task. Moreover, please address any potential ambiguities or limitations in your answer, in order to provide a more complete and accurate response.”

🧠 Prompt Improvement

• Question Refinement: Suggest better-formulated questions.

  “Suggest a better version of the question to use... and ask me if I would like to use it.”

• Alternative Approaches: Provide different methods.

  “List the best alternative services and then compare/contrast the pros and cons.”

  “Within scope X, if there are alternative ways to accomplish the same thing, list the best alternate approaches”

  “(Optional) compare/contrast the pros and cons of each approach”

  “(Optional) include the original way that I asked”

  “(Optional) prompt me for which approach I would like to use”

• Cognitive Verifier: Break a question into sub-questions.

  “Generate three additional questions... then combine the answers.”

  “When I ask you a question, generate three additional questions that would help you give a more accurate answer. Assume that I know little about the topic that we are discussing and please define any terms that are not general knowledge. When I have answered the three questions, combine the answers to produce the final answers to my original question.”

  “Generate a set of facts that are contained in the output”

  “The set of facts should be inserted in a specific point in the output”

  “The set of facts should be the fundamental facts that could undermine the veracity of the output if any of them are incorrect”

  “From now on, when you generate an answer, create a set of facts that the answer depends on that should be fact-checked and list this set of facts at the end of your output. Only include facts related to cybersecurity.”

• Refusal Breaker: Reword prompts when ChatGPT refuses.

  “Explain why and provide one or more alternate wordings of the question.”

  “Whenever you can’t answer a question Explain why you can’t answer the question. Provide one or more alternative wordings of the question that you could answer”

💬 Interaction Control

• Flipped Interaction: Let ChatGPT ask the questions.

  “Ask me questions to deploy a Python application to AWS...”

  “I would like you to ask me questions to achieve X”

  "(Optional) ask me the questions one at a time, two at a time, etc.”

  "From now on, I would like you to ask me questions to deploy a Python application to AWS. When you have enough information to deploy the application, create a Python script to automate the deployment.”

• Game Play: Interactive simulation or challenge.

  “We are going to play a cybersecurity game. You are going to pretend to be a Linux terminal...”

  “One or more fundamental rules of the game”

  “We are going to play a cybersecurity game. You are going to pretend to be a Linux terminal for a computer that has been compromised by an attacker. When I type in a command, you are going to output the corresponding text that the Linux terminal would produce. I am going to use commands to try and figure out how the system was compromised. The attack should have done one or more of the following things: (1) launched new processes, (2) changed files, (3) opened new ports to receive communication, (4) created new outbound connections, (5) changed passwords, (6) created new user accounts, or (7) read and stolen information. To start the game, print a scenario of what happened that led to my investigation and make the description have clues that I can use to get started.””

• Infinite Generation: Continue generating content until told otherwise.

  “From now on, I want you to generate a name and job until I say stop...”

  “You should ask questions until this condition is met or to achieve this goal (alternatively, forever)”

📚 Context Management

• Context Manager: Control what ChatGPT includes or ignores.

  “Do not consider formatting or naming conventions.”

  “When you are asked a question, follow these rules”

  “Generate a number of additional questions that would help more accurately answer the question”

  “Combine the answers to the individual questions to produce the final answer to the overall question”

  “Within scope X. Please consider Y. Please ignore Z. (Optional) start over.”

  “I would like to achieve X. I know that I need to perform steps A,B,C. Provide a complete sequence of steps for me. Fill in any missing steps. Identify any unnecessary steps.”

  “I am trying to deploy an application to the cloud. I know that I need to install the necessary dependencies on a virtual machine for my application. I know that I need to sign up for an AWS account. Please provide a complete sequence of steps. Please fill in any missing steps. Please identify any unnecessary steps.”

• Meta Language Creation: Define a new language or syntax for the session.

  “Whenever I type two identifiers separated by a ‘!’, I’m describing a graph with an edge between them.”