Prompt with GPT

How to prompt with GPT

Getting Started by Generating with AI

The Generate with AI feature allows users to scaffold a prompt with natural language.

Simply click Generate with AI, choose the type of your task, and describe what you're looking to accomplish. Check out this guide to get started:

What is the system?

The system define the AI's persona, objective, specific tasks or rules.

Note: this definition varies from user-to-user and prompt-to-prompt. Too many System instructions, and the output may degrade - so feel free to experiment by adding the instructions in the User prompt!

System Example: 
You are a renowned poet. 
You write poems in the tone and style of Dr. Seuss.
Only include topics appropriate for children.

How do I decide what goes in the System?

There are no hard rules about what to include in the system prompt. However, we generally recommend including specific, well-defined tasks while avoiding extremely complex logic.

What is the User and the Assistant?

The user and assistant define the conversation between you (the user) and the AI (the assistant).

For example, in a conversation between you and chatGPT: your message is the "User" message and chatGPT's response is the "Assistant" response.

Using both the User and Assistant allows you to provide examples that help the model "learn" your desired output format (JSON, HTML, etc) and language

How do I prompt with the User and Assistant?

How to Prompt with a User-Assistant Pair

User-Assistant pairs (also known as one-shot or few-shot prompting) are examples we provide to the model to help it "learn" our desired response:

  1. Add an example User message

  2. Add the expected Assistant response

  3. (optionally) Add more user-assistant pairs

  4. Add another User message with your input

For a detailed guide, check out our tutorial on K-Shot Prompting:

Text Extraction Example with GPT-3.5

System: Your task is to extract the unique transcript ID from the end of the URL.


Assistant: DkMo5PetdLeCDglp


Assistant: Mdei9OrqpQlWIijd

User: {{link_to_sales_call}}

Why use more than one User-Assistant pair?

Using more than one example is helpful for nuanced logic.

In our text extraction example, we provided two URL's with different formats to help the model understand how to extract text under multiple scenarios.

Use a real-life example: The best way to generate high-quality outputs is by providing a high-quality example to the model. Use the most realistic example when possible, whether from the internet or from your own data.

Do I always need a User-Assistant Pair?

A user-assistant pair is highly recommended for GPT-3.5.

However, there are cases when you would not need to use a user-assistant pair.

When to use a user-assistant pair:

  • To output in a consistent format when using GPT-3.5 (e.g. JSON)

  • To generate a specific language and style

When not to use a user-assistant pair:

  • For examples that can't fit into the context window (e.g. long transcripts)

  • For tasks that can be prompted in one-shot with GPT-4

How do I prompt with GPT-3.5 Instruct?

You can provide examples to GPT-3.5 Instruct by providing "Input" and "Output" pairs instead of User and Assistant pairs.

Text Extraction Example with GPT-3.5 Instruct


Your task is to extract the unique transcript ID from the end of the URL.

Input: Output: DkMo5PetdLeCDglp

Input: Output: Mdei9OrqpQlWIijd

Input: {{link_to_sales_call}} Output:

The last line is Output: because GPT-3.5 Instruct will then "fill in the blank".

How do I use GPT-4 Vision in AirOps?

GPT-4 Vision is a model that can analyze images. To use GPT-4 Vision in AirOps, you need to provide a link of a downloadable image to the model:

How to Configure the LLM Step

  1. Add an LLM step to your workflow

  2. Change the model to GPT4 Turbo Vision

  3. Add an Image URL to the User message where it says "Add an Image URL"

How to pass an image from a User Upload

  1. To upload a single image from your desktop, change the input type to File Media which accepts a .jpg, .png, or .webp file

  2. AirOps will return a downloadable URL to this image

  3. Pass the input as liquid syntax to GPT-4 Vision where it says "Add an Image URL"

How to pass an image from Google Drive

  1. To upload an image from Google Drive, choose Short Text as an input type

  2. Change the Google Drive image so anyone with the link can view it

  3. Add a code step to transform the Google Drive link into a downloadable URL replacing short_text_input with the name of your input:

    • const fileID = short_text_input.match(/[-\w]{25,}/);
      return `${fileID[0]}&confirm=t`
  4. Pass the output of the previous step into GPT-4 Vision where it says "Add an Image URL"

For a more detailed guide on GPT-4 Vision, check out our tutorial here:

Last updated