AI Builder

The AI Builder is a function that allows for conversation with AI, connecting with OpenAI via an OpenAI key, all via the spreadsheet.

AI Builder Properties

The properties panel consists of a single AI BUILDER drawer. This guide will describe the general and styling properties only; the dynamic visibility properties are generic, and a separate guide and tutorial on dynamic visibility can be found here.

For more information on property panels, see the article on how to Set Property Values


AI BUILDER

  • OpenAI Key - Enter a key generated by OpenAI. This can be done

  • Personality Presets - Select an item from the dropdown to define an AI personality:

    • ChatGPT Default

    • Analytical Expert

    • Strategic Advisor

    • Story Teller

    • Technical Assistant

    • Business Consultant

    • Custom

  • Personality Description - define the personality description.

All options but Custom will have a pre-defined personality that can be edited, e.g.

ChatGPT Default: "You are a helpful and friendly AI assistant. Your goal is to assist users with a wide range of questions, from technical topics to general conversation. You provide clear, engaging, and informative responses while maintaining a professional yet approachable tone."

  • Model - Select from the dropdown and define the OpenAI model used.

OpenAI offers many models, each serving a specific purpose. GPT-4.1 and GPT-4.1 mini are the most flexible, which is why they power ChatGPT. o3, o3-pro, and o4-mini deliver advanced reasoning for solving complex problems, while GPT-4.1 nano focuses on speed and affordability. There is certainly a significant amount of overlap in the capabilities of the different models, but generally, one should stand out as the best balance between power and price.

  • Temperature - adjust the creativity of the AI model. Ranges from 0 to 2, from least to most creative. The higher the value, the more inconsistent and ambiguous it can be

  • Max Tokens - Define the maximum number of tokens that can be used with the AI model.

  • Tokens are units of text that AI models use to understand and generate responses.

    • 1 token = ~ 4 characters or ¾ of a word

      • 1 million tokens = ~750,000 words (about a whole book)

      • You can use tools such as Tozenizer to see how units of text are ready by OpenAI

  • There are input tokens (your prompt) and output tokens (the model's response)

    • Example: If you send 100 tokens as input and receive 200 tokens as output, you'd be charged for 300 tokens.

  • Series - create multiple AI bots with a single function by adding multiple series.

    • Name - Enter a value to name the series

    • Source - Bind to a cell containing the information that is being sent to the AI tool

    • Destination - Bind to a cell that will return the results of the query to the AI tool

  • Keep Chat Memory - check this to save all previous chat responses and questions in sent to the AI. This is unchecked by default

  • Triggered by - set a trigger for the AI using conditional logic

Last updated

Was this helpful?

Revision created