Hello, how can we help you?

Recent Searches: Learn about SoftExpert Competência - Register evaluation plan - SoftExpert Competency Queries - SoftExpert Competency Tasks

Automating workflows with AI

 

 

This content was generated by artificial intelligence. To request a review, send an e-mail to documentacao_se@softexpert.com.

 

 

Prerequisites

 

Presentation

In the BPM solution (comprising the SoftExpert Workflow , SoftExpert Form , and SoftExpert Process components), Artificial Intelligence (AI) is used to optimize and transform business processes through the automatic execution of activities. 

This article will demonstrate the use of AI in BPM solutions to automate workflows.
 

Configure command and web service

Before using automation in the workflow, it is necessary to configure a command and the web service in the system activity that will receive the automation. See an example below:

1. Access the Process menu (PM063).

2. Research the desired process.

3. With the process selected, click the Open flowchart button.

4. In the process flowchart, double-click the system activity where the AI ​​will be applied.

5. On the General Data tab , under Integrations, select Web Service

6. Click on Web Service Configuration and configure the SoftExpert Ask AI data source 

7. In the Formula (Before execution) field, click Formula Editor and enter the command that the AI ​​will receive.

Example command

//generate prompt

prompt = "You are an incident specialist who is responsible for analyzing an incident description and decide if is ou not is an incident. "
prompt = prompt +" Tag <incident> contain the incident description."
prompt = prompt +" <incident>"
prompt = prompt +" "+ VALORCAMPO('ITIL';'txincident')
prompt = prompt + " <\\incident>"
prompt = prompt +" The answer is only YES or NO."
prompt = prompt +" The response should be a single text (YES or NO) that represents if is or not is an incident."
prompt = prompt +" Do not return an explanation of why you selected it."


RETORNO DEFINECAMPOTABELA('ITIL';'txprompttriage';prompt)
 

8. After entering the formula, click Save and Exit.

9. After configuring the command and the web service, click Save and Exit again. The automation will then be ready to run.

 

How workflow automation works in practice.

To understand how workflow automation works, consider the following context: an organization has an incident management process, which brings together all the activities necessary for incident identification. 

Below are examples of how AI can be used at each stage of the incident management process:

Process step 

Use of AI
Incident report
  • The user registers the incident in the form
  • When the process is forwarded to the next stage, the AI ​​will automatically triage it and decide whether or not it is an incident.
  • AI can also be used in the user-filled form to assist in describing the incident.
 Screening
  • AI performs the initial screening, identifying whether the record is an incident or not.
 Categorization
  • The AI ​​categorizes the incident to route it to the most appropriate team. If it is not considered an incident, the process is terminated. 
  • It is possible to see the path followed by the process by accessing the flowchart through the execution activity.
Forwarding to the responsible team.
  • The AI ​​sends the incident to My Tasks > Task Execution for the responsible team.
  • The responsible team must complete a resolution for the incident and, if necessary, may use AI to improve the resolution description before forwarding the process to the next step.
Impact analysis
  • The AI ​​generates an impact analysis based on severity and decides whether it will be necessary to create an action plan, complete the feedback process, or both.
Investigation and diagnosis of the incident
  • If the AI ​​identifies that the incident is high-impact, a thorough investigation with an action plan will be necessary.
  • It is possible to use AI to generate the actions of the action plan.
User feedback
  • It uses AI to generate sentiment analysis and insert it into the form.
  • Sentiment analysis utilizes the SoftExpert Sentiment Analysis data source , which has a pre-configured command to analyze texts and identify the predominant sentiment, classifying it as positive , negative , or neutral . In addition to the classification, a numerical score is provided for each sentiment, allowing for a more detailed analysis.

The following video illustrates the information in the table:

 

Conclusion

The use of Artificial Intelligence (AI) to automate workflows not only facilitates sorting, categorization, and analysis, but also contributes to more agile management, minimizing errors and increasing the accuracy of decisions made throughout the process stages.


Was this article helpful?