Mountains and greenery next to text that says "Get Better Natural Language Search Results."

How to Get Better Natural Language Search Results

By

We’re very excited to announce that we’re enhancing the natural language features as part of Einstein Search. As of Summer 2021, Einstein Search, which includes personalization, actionable results, and natural language capabilities, has been the default search experience for customers within the Lightning Experience.

More specifically, Natural Language Search allows users to type queries into the Global Search bar, which makes completing CRM tasks easier. Popular natural language queries that users enter in the Global Search bar include “my open cases” or “closed opportunities in California”. One of the common requests we’ve heard from our customers is to control the way the system interprets certain queries. For example, if the user knows exactly which subsidiary of an account the query they wrote is referring to, or if there are certain words in the query that refers to multiple parts of the CRM system, then they should be able to edit the Natural Language Search results quickly instead of submitting a completely new query to the system.

We are making this pilot open to all interested admins so that we can gather feedback in order to prioritize future improvements before making this feature generally available (GA). As part of this open pilot, admins can enable this functionality through the Setup page which will, in turn, give users more control of how their query is interpreted. More specifically, if there are multiple ways the system can understand a query, the user now has the flexibility to pick the interpretation they intended.

Natural Language Search examples

Here are two examples of the current Natural Language Search and how this new pilot feature allows the user to adjust Einstein Search’s interpretation of the search query.

When a user enters a query to look for accounts in New York, they would enter “accounts in New York” in the search bar. However, the user may have meant to find the accounts in either the city of New York or the broader state of New York. The UI can now present the user with an initial set of results alongside a set of editable filter options, so that user can easily adjust the system’s interpretation in real time.

The user editable filter option for Natural Language Search.

Let’s review another example. A user is looking for contacts in a medical organization and enters “medical contacts” in the search. The user may be intending to get to a specific organization but is not able to recall the exact name. With this enhancement, the user can easily select the right record with the help of secondary fields, such as phone number, to easily disambiguate between subsidiaries of a specific organization.

An editable filter for the Natural Language Search using a secondary field such as phone number.

Enable the open pilot in Setup today!

To allow your users to take advantage of this feature, in Setup, navigate to Einstein Search → Settings, and then enable Natural Language Search filters. Make sure that Natural Language Search on the top section remains checked. This will allow users to get this experience across all editions using Lightning Experience.

 Einstein Search Setup page where an admin can check the box for Natural Language Search filters (requires Natural Language Search).

We would love to hear your feedback! Please engage us on our Trailblazer Community (#Einstein Search) or drop me a note at mukund.ramachandran@salesforce.com.

Resources

≈

AI for Admins: How to Choose the Right Einstein Builder for Your Business Needs

Salesforce Einstein was launched in 2016 with a mission to deliver artificial intelligence (AI) into the hands of admins, developers, and business users, helping make Salesforce the world’s smartest CRM. Since then, the Einstein Platform has grown exponentially. Today, it powers more than 116 billion predictions per day for companies of all sizes across the […]

READ MORE
AI for Admins blog series post on Einstein Case Classification

AI for Admins: What You Need to Know to Make Einstein Case Classification a Success

Many Salesforce Admins are looking for ways to help scale their organization’s customer service experience. This can include finding solutions to increased case volume and optimizing agents’ time so they can solve customer issues faster, instead of just triaging them. One way to accomplish all of this is with Einstein Case Classification. So let’s take […]

READ MORE

Have an Idea for a Story?

We are all about the community and sharing ideas.
Do you have an interesting idea or useful tip that you want to share?

SHARE YOUR IDEA