Brings power of harmonized record from Data Cloud to CRM.
1.Copy Field Enrichments
Copy high-value fields from Data Cloud records to your Contact and Leads.
2.Related List Enrichments
Add DMO Related lists to your Contact and Lead SObjects.
Brings power of harmonized record from Data Cloud to CRM.
1.Copy Field Enrichments
Copy high-value fields from Data Cloud records to your Contact and Leads.
2.Related List Enrichments
Add DMO Related lists to your Contact and Lead SObjects.
This Ingestion API will be helpful to send interaction-based data to Data Cloud in near real-time and
this is getting processed every 15 minutes.
Salesforce Ingestion API is a RESTful interface that allows you to load data into Data Cloud programmatically. This API supports two patterns:
Streaming Pattern, which uses JSON as its format and is suitable for loading data in micro-batches through the REST API.
Bulk Pattern, on the other hand, employs the CSV format and loads data using jobs.
Note :
The streaming pattern accepts incremental updates to a dataset as those changes are captured, while the bulk pattern accepts CSV files in cases where data syncs occur periodically.
When to use Streaming vs Bulk ingestion?
Streaming Ingestion :
When updating small micro-batches of records in near real-time.
When using data source systems that are built on modern streaming architectures.
When creating Change Data Capture events.
When consuming data from webhooks.
Bulk Ingestion :
When moving large volumes of data on a daily, weekly, or monthly schedule.
When using legacy systems, where you can only export data during off-peak hours.
When using a new Data Cloud org that you want to backfill with 30, 60, or 90+ days of data
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.