Create and Edit IT Service Knowledge Articles with Einstein
Create contextual knowledge articles from incident, problem, and change request records
using generative AI. Reduce manual effort and standardize documentation by converting
information from your IT service records into structured knowledge.
Required Editions
Available in: Lightning Experience
Available in: Enterprise, Performance, and Unlimited
Editions with Agentforce IT Service.
Einstein uses specific prompt templates for incidents, problems, and change requests and the
data from the IT service record to generate a consistent article. It extracts key details such
as symptoms, root causes, and resolutions, and outputs a draft using the following common
fields: Title, Summary, Issue, Workaround, Root Cause, and Resolution.
Click Draft with Einstein on an Incident, Problem, or Change Request
record. Enter a relevant title for the knowledge article. If the title is too different from
the details in the record, Einstein fails to draft an article. The article is created in a
draft state and requires your review or approval.
Here's how Einstein-based knowledge creation works for IT service records:
Incident: Einstein analyzes the incident's subject and description, as well as data from
related and parent incidents, and resolution summaries. The output focuses on the employee's
issue, temporary workarounds, and resolution steps to aid immediate troubleshooting.
Problem: Agentforce IT Service supports generating a Known Error document by extracting
key details from the problem record, directly supporting the workflow for documenting
confirmed root causes and workarounds. Einstein specifically looks at the problem's
workaround, root cause summary, and data from parent and related problem records. The output
clearly defines the root cause and workaround which help when you are using Einstein to
create a Known Error article.
Change Request: If you used the sample prompt to create the template for change requests,
Einstein analyzes the request's business justification, impact analysis, and implementation
documents like the remediation plan, test plan, and implementation plan. The output reflects
the change process, with the issue field capturing the reason the change was implemented and
the resolution field documenting the details of the deployed fix.
We use three kinds of cookies on our websites: required, functional, and advertising. You can choose whether functional and advertising cookies apply. Click on the different cookie categories to find out more about each category and to change the default settings.
Privacy Statement
Required Cookies
Always Active
Required cookies are necessary for basic website functionality. Some examples include: session cookies needed to transmit the website, authentication cookies, and security cookies.
Functional Cookies
Functional cookies enhance functions, performance, and services on the website. Some examples include: cookies used to analyze site traffic, cookies used for market research, and cookies used to display advertising that is not directed to a particular individual.
Advertising Cookies
Advertising cookies track activity across websites in order to understand a viewer’s interests, and direct them specific marketing. Some examples include: cookies used for remarketing, or interest-based advertising.