Low-code or no-code — either way we’re stoked about the release of Einstein 1 Studio.

When Salesforce first announced Einstein Copilot, the conversational AI assistant for CRM, users had the option to pick from a selection of standard prompts with some options for customization.

Now Salesforce admins and developers can customize Einstein Copilot using low-code tools available in Einstein 1 Studio including:

• Copilot Builder - Allows users to create custom AI actions to accomplish specific business tasks
• Prompt Builder - Helps users build and activate custom prompts in the flow of work
• Model Builder - Where users can build or import a variety of AI models

Customers can access Einstein 1 Studio by purchasing Einstein 1 Editions or by adding it on to Enterprise or Unlimited Editions.

Einstein 1 Studio: Unlock the Power of AI Across Your Business

Einstein 1 Studio is deeply integrated with Data Cloud, which unifies trapped data and grounds AI models with a comprehensive understanding of customer data and metadata.

Compared to ChatGPT where you simply enter a question and receive an answer (sometimes relevant, sometimes not), Einstein 1 Studio safely utilizes your customer data to provide accurate and insightful insights and recommendations. 

Let’s take a closer look at the tools available in Einstein 1 Studio.

Copilot Builder (Beta)

Currently in beta, Copilot Builder allows companies to customize Einstein Copilot to meet their business needs with custom actions.

With Copilot Builder, Salesforce admins and developers can use tools they already have (Apex, Flow, and MuleSoft APIs) as well as prompts, to enable Einstein Copilot to complete tasks. Einstein Copilot can use these custom actions to complete tasks across any Salesforce app or external system.

For example, a user could ask Einstein Copilot to create an invoice for an account with specific products and apply a discount (pictured above). Using custom actions built with customer data and metadata, Einstein Copilot can complete this task by referencing the record name and executing a MuleSoft API to create the purchase order on NetSuite.

It may not be magic, but it sure feels like it when you can complete a task in a few clicks. More Copilot Builder updates will likely follow in the coming months. 

Prompt Builder

Prompt Builder helps Salesforce admins and developers simplify complex tasks and processes by equipping them with the power to create custom AI prompts without code. Prompts can be designed and repurposed everywhere in Einstein Copilot, Lightning pages, and Flows.

Prompts are grounded in data from CRM, Data Cloud, and external sources — ensuring users receive accurate and informative responses when creating prompts. Unlike other AI tools that require users to switch between external systems, Prompt Builder is fully integrated within the flow of your work in Salesforce.

For instance, a custom prompt can be embedded in a contact record as a button, allowing a service agent to get a snapshot of all escalated cases for a customer in one click.

Model Builder

With Einstein 1 Studio, companies can leverage their customer data from Data Cloud to train AI models that solve specific business needs.

While some alternative solutions only allow businesses to utilize a single Large Language Model (LLM), Einstein 1 Studio allows companies to connect to a variety of AI models. Businesses can use predictive and generative AI models and services from Salesforce partners, including Amazon Web Services (AWS) via Amazon Bedrock and Amazon SageMaker, Anthropic, Azure OpenAI, Cohere, Databricks, Google Cloud’s Vertex AI, and OpenAI.

Using clicks, admins can connect and deploy the models in Salesforce. Once deployment happens, predictions are automatically and continuously updated in near real time to generate accurate and tailored insights.

A use case might be that a company wants to be able to predict their customers’ product preferences in order to deliver personalized product recommendations. Model Builder could be used to leverage Customer 360 data in Data Cloud’s integrated profiles to develop AI models. These models would then be able to forecast an individual’s product preferences. 

Model Builder support for fine-tuning LLMs on Data Cloud data will be available later this year, starting with Amazon Bedrock, Google Vertex AI, and OpenAI LLMs.

Parting Thoughts: Einstein 1 Studio Empowers Business to Embed AI Across Every Salesforce App and Workflow

With AI positioned as the #1 technology IT teams feel pressure to onboard quickly, Einstein 1 Studio provides businesses with low code solutions for embedding AI across any app for every customer and employee experience.   

Businesses need user-friendly interfaces that make it easy to interact with AI in the flow of work and Einstein 1 Studio offers a powerful set of tools that can be accessed directly in Salesforce.

The tools available in Einstein 1 Studio — Copilot, Prompt, and Model Builder — allow Salesforce admins and developers to customize Einstein Copilot as well as build and modify prompts and actions to meet the unique needs of businesses across industries.

With the ability to build AI apps by customizing AI across Salesforce apps and workflows, companies can boost productivity, improve customer experiences, and unify customer data. By integrating Einstein 1 Studio into your suite of Salesforce tools, businesses of all sizes can take full advantage of generative AI. 

Want to learn more about how you can take your business to new heights with the latest Salesforce AI products and features? Get in touch with us today and let’s chat!