Einstein AI Connector 1.0 - Mule 4
Anypoint Connector for Einstein AI (Einstein AI Connector) provides connectivity to LLMs via the Salesforce Einstein Trust Layer.
Einstein AI Connector offers a range of advanced features that simplify and enhance AI integration in MuleSoft applications.
Use this connector to:
-
Build AI Agents in a low-code environment
-
Leverage existing investments (APIs, integrations, and templates) as tooling for the AI agents
-
Manage all Large Language Model (LLM) interactions through the Salesforce Einstein Trust Layer
-
Generate vector embeddings to power RAG-based architectures
For information about compatibility and fixed issues, see the Einstein AI Connector release notes.
Before You Begin
To use this connector, you must be familiar with:
-
Anypoint Connectors
-
Mule runtime engine (Mule)
-
Elements and global elements in a Mule flow
-
How to create a Mule app using Anypoint Code Builder or Anypoint Studio
Before creating an app, you must have:
-
Java 8 or 17
-
Apache Maven
-
Connected App credentials to connect with your Salesforce org
-
Anypoint Platform
-
The latest versions of Anypoint Code Builder or Anypoint Studio
To configure the connector, you must create a Connected App in Salesforce. For more information, see Models API Developer Guide.
Common Use Cases for the Connector
These are some common use cases for Einstein AI Connector:
-
Enhance customer service by providing case summaries, case classifications, large dataset summaries, and more.
-
Assist sales teams in writing sales emails, summarizing cases for specific accounts, assessing the probability of closing deals, and more.
-
Support marketing teams in generating product descriptions, creating newsletters, planning social media campaigns, and more.
-
Generate embeddings of text data to support sentiment analysis and natural language understanding applications.
Next Step
After you complete the prerequisites, you are ready to create an app and configure the connector using Anypoint Studio.