Skip to main content

Key concepts

Key concepts related to GPT for Work add-ons and the use of ChatGPT and other AIs directly from MS Excel, and Word, Google Sheets and Docs.

AI concepts​

Prompt​

Input text given to the model to generate a response or perform a task. Prompts can be included in the sidebar of the GPT for Work add-ons, or passed as arguments in GPT functions. For guidance, see Write a good prompt.

Model​

Language model in use in GPT for Work add-ons, such as OpenAI GPT-4o or Anthropic Claude 3.5 Sonnet. You select the model in the sidebar of the GPT for Work add-ons. Available models depend on the add-on and whether you are using your own API key. For more information, see Supported models.

AI provider​

Company that provides models to GPT for Work add-ons. GPT for Work integrates with multiple AI providers, including OpenAI, Anthropic, and Google. See the full list of supported models by provider for each add-on.

Custom instructions​

Specific guidelines provided to the model to define its role, expertise, or how it should respond to prompts. Custom instructions are set in the sidebar of the GPT for Work add-ons, and remain active in the document or spreadsheet until you change them.

API key​

Unique identifier that gives access to models from AI providers such as OpenAI or Anthropic. You don't need an API key to use GPT for Work add-ons, except for GPT for Docs, which is currently free to use with your own API key. Using your own API key gives you more model options, control, and privacy. It can also lower your costs if you're on self-service pricing.

Tokens​

Small pieces of text that can represent a word or subword, a punctuation sign or a symbol. Models split all input and output into tokens for efficient processing. The token is the basic unit of usage of model providers. The number of tokens used in the prompt (input) and the AI's response (output) impacts your balance if you're on self-service pricing.

Rate limits​

Restrictions on the number of tokens or on the number of requests that can be processed within a certain timeframe (minute, day, month). AI providers set rate limits on their models. Google also enforces rate limits on the daily number of requests. Learn more.

GPT for Work concepts​

Panel in GPT for Work add-ons where users can interact with the AI, input prompts, and adjust settings. When you launch the GPT for Work add-ons, the sidebar opens on the right side of the screen.

Excel add-on

Bulk tools​

Bulk tools allow you to run prompts on an entire spreadsheet column at once without writing any formulas. You configure and run bulk tools from the add-on sidebar.

GPT for Work provides dedicated bulk tools for selected use cases, such as classification, translation, and web search, as well as a generic bulk tool for custom prompts.

Bulk tools in the sidebar

For more information, see Bulk tools in GPT for Excel and Bulk tools in GPT for Sheets.

GPT functions​

GPT functions are custom spreadsheet functions that allow you to run AI prompts from inside spreadsheet cells. GPT functions work exactly like native spreadsheet functions in that you can nest them and combine them with other functions.

GPT for Work provides dedicated GPT functions for selected use cases, such as classification, summarization, translation, and web search, as well as a generic GPT function for all other use cases. You can define function-specific parameters to further refine how the AI generates responses. You can find a list of all available functions with usage examples in the add-on sidebar.

List of GPT functions

For more information, see GPT functions in GPT for Excel and GPT functions in GPT for Sheets.

Formula assistant​

The formula assistant allows you to generate spreadsheet formulas based on plain-language descriptions of what you want to achieve. You can also use the formula assistant to explain existing formulas (in English).

The formula assistant is available in the add-on sidebar, both under Bulk tools and GPT functions.

Formular assistant in the sidebar

On this page