How UiPath Discovery Suite supports identification of Agentic Process Automation (APA)

📚 Understand the basics of the newly persona-based LLM-powered Agentic Process Automation and discover how existing UiPath Discovery Suite products like Communication Mining, Process Mining, and Task Mining can be leveraged to identify APA candidates.

Topics Covered:

💡 Idea Behind APA: Explore the innovative concept of Agentic Process Automation and its significance in modern workflows.

🔄 How APA is Different from RPA: Learn the key differences between Agentic Process Automation and Robotic Process Automation.

🚀 Discover the Advantages of APA: Uncover the unique benefits of implementing APA in your organization.

🔍 Identifying APA Candidates with UiPath Discovery Products: See how UiPath's Communication Mining, Process Mining, and Task Mining tools can help pinpoint potential APA candidates.

🔮 Discussion on Expected Future Impacts: Engage in a discussion on the potential future impacts of APA on various industries and business processes.

Enhance your knowledge on the forefront of automation technology and stay ahead with Agentic Process Automation. 🧠💼✨

Speakers:
Arun Kumar Asokan, Delivery Director (US) @ qBotica and UiPath MVP
Naveen Chatlapalli, Solution Architect @ Ashling Partners and UiPath MVP

1. How UiPath Discovery Suite supports
identification of Agentic Process Automation
(APA)
Session Date: 07/16/2024
Speakers: Naveen Chatlapalli & Arun Kumar Asokan

2. Solution Architect
Ashling Partners
UiPath MVP 2024
UiPath Dallas Chapter Lead
Naveen Chatlapalli
Organizers/Team
Diana Gray
Community Leader
Community Marketing Manager
UiPath
Automation Delivery Leader
qBotica
UiPath MVP 2024
Arun Kumar
Asokan

3. Overview of Agentic Process Automation
How is it different from RPA
Discover the Advantages of APA
Identifying APA Candidates with UiPath Discovery Products
Discussion on Expected Future Impacts
Agenda

4. Overview of Agentic Process Automation
Overview
●Advanced automation technology leveraging Large Language Models (LLMs)
●Uses AI agents to manage and execute complex tasks requiring human-like
intelligence
●Significant evolution from traditional Robotic Process Automation (RPA)
Key Components
●Agentic Workflow Construction LLM-based agents create workflows from human
instructions
●Agentic Workflow Execution AI agents monitor and manage workflows
●AI Agents Powered by sophisticated AI and machine learning algorithms

6. Overview of Agentic Process Automation
Image Ref: arXiv:2311.10751v2

7. How is it different from RPA

8. Discover the Advantages of APA
Benefits of APA
●Increased Efficiency: Automates complex processes, reducing the need for human
intervention.
●Reduced Human Error: Enhances accuracy by minimizing manual errors.
●Adaptability: Adjusts to variable scenarios, making it suitable for diverse
applications.
●Focus on Creative Tasks: Frees up human workers to focus on more strategic and
creative tasks.
Applications of APA
●Manufacturing: Optimizes supply chain management and production processes.
●Finance: Automates complex financial transactions and compliance reporting.
●Healthcare: Streamlines patient data management and billing processes.
●Customer Service: Enhances customer interactions through intelligent automation.

9. Identifying APA Candidates with UiPath Discovery
Products
Automation Hub: Process assessments can be tailored to identity APA
candidates.
Task mining : Assisted Task mining can help with identifying persona based
long running complex tasks along with Agentic Skill Discovery in existing
processes executed by humans.
Process mining : Major Process variations, non conformance and
inefficiencies in existing process will help identity APA candidates.
Communication mining : Large intent frequency requests and low ‘Quality of
Service’ (QoS) scores will help identify APA candidates.

10. Identifying APA Candidates with UiPath Automation
hub

11. Identifying APA Candidates with UiPath
Task Mining(TM)
TM-APA Candidate Identification pattern 1: Long running multi hour end
to end process performed by a person with multiple variations e.g. Tax
filing application .
TM-APA Candidate Identification pattern 2 : Task gets into a multiple
swill chair exchanges between multiple team members and software
programs e.g. Claims processing
TM-APA Candidate Identification pattern 3 : Persona based task catalog
identification which can become the Agentic Skill Discovery activity which
results in updated Agentic tool set e.g. Mortgage Underwriter persona
based agentic toolset for assessing, approving or rejecting mortgages.

12. Identifying APA Candidates with UiPath
Process Mining(PM)
PM-APA Candidate Identification pattern 1 : Identify process areas that are
contributing to non conformance and inefficiencies like frequent bottleneck in
the process e.g. Legal approvals
PM-APA Candidate Identification pattern 2 : Using simulate automation
opportunity to identity critical but non highlighted process steps e.g. Bill of
lading for international carrier
PM-APA Candidate Identification pattern 3 : Process that have many
exception and failures(no auto healing) i.e. rework e.g. IT build deployment
and release process.

13. Identifying APA Candidates with UiPath
Communication Mining(CM)
CM-APA Candidate Identification pattern 1 : High volume priority messages
on a particular intent or cluster e.g. IT support escalation emails
CM-APA Candidate Identification pattern 2 : Tone and Quality of
Service(QoS) is negative for extended period e.g. Mortgage closing
communications.
CM-APA Candidate Identification pattern 3 : Multiple and complex requests
in a single customer or vendor communication e.g. Life insurance policy term
changes along with new address and dependent additions.

14. Discussion on Expected Future Impacts
Highly flexible and adaptive systems: Recent changes improve system
predictability, ensuring reliable workflow execution outcomes consistently.
e.g. IROBOT
Fault tolerant and Auto healing : Process success rate and ROI
improvement due to built in auto healing capability to minimize human
intervention. e.g. Terminator/ Enthiran /ROBO
Human Agent Collaboration : Human and software agents will
collaborate seamlessly to perform work and in near future Agents can
even independently run certain parts of the business functions
independently or minimal human supervision e.g. THE MATRIX
Don’t forget the “KILL” switch for Agents before they infect the whole MATIRX !!!

15. UiPath Discovery documentation :
•Automation Hub -https://docs.uipath.com/automation-hub/automation-cloud/latest
•Process mining -https://docs.uipath.com/process-mining/automation-cloud/latest
•Task mining -https://docs.uipath.com/task-mining/automation-cloud/latest
•Communication Mining -https://docs.uipath.com/communications-mining/automation-cloud/latest
Research paper:
●FromRPAtoAgenticProcessAutmation -https://www.semanticscholar.org/paper/ProAgent%3A-
From-Robotic-Process-Automation-to-Ye-
Cong/d416ebeee27c2cb6c25acd35fc65f7453398aee9?utm_source=direct_link
●Agentic Skill Discovery -
https://www.researchgate.net/publication/380894878_Agentic_Skill_Discovery
Resources to check

16. Join a UiPath Chapter
•Dallas Chapter: https://community.uipath.com/dallas-texas/
Connect with us on LinkedIn
•Diana Gray: https://www.linkedin.com/in/diana-gray-mba/
•Naveen Chatlapalli: https://www.linkedin.com/in/nchatlapalli/
•Arun Kumar Asokan: https://www.linkedin.com/in/arun-kumar-asokan-mba/
Get Connected!

17. Questions

18. Thank You