Prompt Builder

 Prompt Builder is a generative AI tool in Einstein 1 Studio

that allows you to create reusable prompt templates.

Prompt templates are resolved into prompts and sent to a large

language model(LLM),always going through the Einstein Trust layer,

to get response.

Prompt templates can be securely grounded using data that is not part

of the LLM training data to give the model more context and improve the

accuracy of its responses.

you can choose different types of data providers

like Apex,Flow or merge fields to add context to 

your templates.

  

Prompt Template Type :

1.Sales Email 

 Draft personalized emails through Email Composer.

   Inputs :

    Contact or lead, and optionally another object of your choice.

   Entry points :

    Email Composer,Flow,Apex,REST API and Copilot Action.   

   

2.Field Generation 

 Generate text to be stored in a custom field within a record page.

   Inputs :

    An object of your choice

   Entry points :

    Record page,Flow,Apex,REST API,Copilot Action

3.Record Summary 

 Generate a summary for a record to be used in einstein copilot.

   Inputs : An object of your choice.

   Entry points : Copilot Action

 

4.Flex

  Generate a text to be used anywhere.

  Inputs :

  Up to five objects of your choice.

  Entry points:

   Flow,Apex,REST API,Copilot action

   

Data providers for grounding

When executing a prompt template, data providers can use any of the inputs (or related records) to compute text, which is then added to the prompt that is finally sent to the LLM.

Grounding prompt templates with Flow

Grounding prompt templates with Apex

When to use Flow or Apex for grounding will depend on your preference for using clicks vs code, the complexity of the logic to implement, and the guidelines that your company has for no-code vs code tools usage.