News / Artificial Intelligence

Salesforce Einstein Announces New Copilot Updates: New AI Search and More

By Ben McCarthy

Artificial Intelligence is clearly the trending topic of the moment, but there is an unsung hero waiting on the sidelines for its moment of glory. 

Data Cloud, previously Genie, is a product Salesforce are clearly proud of, and it will be powering many of Salesforce’s best use cases for AI on the Einstein 1 platform. Today, Salesforce have given us a glimpse into the future at World Tour New York, along with a few exciting updates…

Spring ‘24 Release Dates 

Whilst Salesforce have slowly been releasing AI powered products throughout the year, many of us are yet to get our hands on any Einstein GPT products. Well, this may change very soon, as Salesforce have announced that Einstein Copilot & Search will be available from February 2024. Data Cloud unstructured support will also be in pilot in February.

Whilst there doesn’t look to be any hints of AI products being released in the upcoming Salesforce Spring ‘24 release, it’s interesting to note that the main release dates are both in February, so we could get a nice surprise when the Spring ‘24 Release Notes come out next week (December 20). Stay tuned for updates! 

Manage Unstructured Data With Einstein 1

Today at World Tour New York, Salesforce unveiled their latest major update to the Einstein 1 platform, which combines the power of Data Cloud and AI. You will soon be able to manage all of your unstructured data through Data Cloud, which then gives Einstein Copilot the ability to search, retrieve, and make sense of this huge amount of information.

IDC estimates that 90% of business data is unstructured – examples include PDFs, emails, social media posts, and audio files. Forrester have also predicted that the volume of unstructured data managed by enterprises will double by 2024. 

Whilst we all know the value of data, until GenAI came along, a solution to search through all of this unstructured data previously wasn’t readily available to most organizations. Now we have the technology, Salesforce are providing the platform.

Here are a few examples of how this might help your organization:

  1. Customers can receive better customer service via bots. GenAI will be able to search a huge number of PDFs via a knowledge base in order to define the correct answer, and cite their source of the information to the customer.
  2. Sales reps can search through huge amounts of unstructured data in order to prepare for a customer meeting based on emails, phone calls, and meeting notes.
  3. Markers will be able to understand consumer intent by analyzing unstructured survey data, as well as social media posts.

This is a completely new offering by Salesforce as part of Data Cloud, which will require the use of a Vector Database, also supplied by Salesforce. You will also be able to use familiar automations tools such as Flow and Apex in order to monitor for changes in this data, and then trigger workflows. 

In addition to the new Data Cloud Vector Database required to power this storage of unstructured data, Salesforce have also announced Einstein Copilot Search. This tool is currently in closed beta, and has enhanced Einstein Copilot with AI search capabilities that can interpret and respond to complex queries from users. 

How Data Cloud Vector Databases Work

1. Ingest Unstructured Data in Data Cloud

With the help of a new, unstructured data pipeline, relevant unstructured data for case deflection, such as product manuals or upgrade eligibility knowledge articles, can be ingested in Data Cloud and stored as unstructured data model objects.

2. Chunk and Transform Data for Use in AI

In Data Cloud, teams will then be able to select the data that they want to use in processes like search, chunking this data into small segments before converting it into embeddings – numeric representations of data optimized for use in AI algorithms. 

This is done through the Einstein Trust Layer, which securely calls a special type of LLM called an “embedding model” to create the embeddings. It is then indexed for use in search across the Einstein 1 platform alongside structured data.

3. Store Embeddings in Data Cloud Vector Database

In addition to supporting chunking and indexing of data, Data Cloud now natively supports storage of embeddings – a concept called “vector storage”. This frees up time for teams to innovate with AI instead of managing and securing an integration to an external vector database.

4. Analyze and Act on Unstructured Data

Use familiar platform tools like Flow, Apex, and Tableau to use unstructured data, such as clustering customer feedback by semantic similarity and creating automations that alert teams when sentiment changes significantly.

5. Deploy AI Search in Einstein Copilot to Deflect Cases 

With relevant data, such as knowledge articles, securely embedded and stored in Data Cloud’s vector database, this data can also be activated for use in Einstein AI Search within Einstein Copilot. When a customer visits a self-service portal and asks for details on how to return a product, for example, the Einstein Copilot performs semantic search by converting the user query into an embedding, after which it compares that query to the embedded data in Data Cloud, retrieving the most semantically relevant information for use in its answer while citing the sources it pulled from.

The end result is AI-powered search capable of understanding the intent behind a question and retrieving not just article links but exact passages that best answer the question, all of which are summarized through a customer’s preferred LLM into a concise, actionable answer – boosting customer satisfaction while deflecting cases.

Source: Salesforce

Learn more:

The Author

Ben McCarthy

Ben is the Founder of Salesforce Ben. He also works as a Non-Exec Director & Advisor for various companies within the Salesforce Ecosystem.

Leave a Reply