Download as PDF, PPTX
More Related Content
Similar to Presentation Session 1 - Introduction to Agentic.pdf
More from Rohit Radhakrishnan
Presentation Session 1 - Introduction to Agentic.pdf
- 1. Transitioning to agenticautomation 6 Part webinar series by the UiPath Community March – April 2025
- 2. 2 Meet the team! SatishPrasad Solution Consultant @ IRIS UiPath MVP Rohit Radhakrishnan Community Lead - Asia Pacific & Japan @ UiPath Mannoj Batra Vice President @ NatWest Group UiPath MVP Mukesh Kala RPA Manager @ Boundaryless Group UiPath MVP Vibhor Shrivastava Director Community Advocacy @ UiPath
- 3. 3 Join UiPath CommunityDays Chennai April 5, 2025 | Saturday 8 am onwards Scan the code to register Pune April 12, 2025 | Saturday 8 am onwards Scan the code to register Be part of the first agentic automation community
- 4. 4 6 Part Series Registerfor each session here
- 5. 5 Let's Start Simple 1.Manual Car This is the starting point, where everything depends on human effort. Example: A child plays with a manual toy car, pushing it around using their hand. If the car gets stuck, the child has to physically move it around the obstacle. The car cannot do anything on its own. Characteristics: • Entirely dependent on the user for movement. • No automation or intelligence—every action is manual. • If the child doesn’t push it, the car does nothing. In the context of automation: The manual car represents No automation at all—every action in a task is done by a human.
- 6. 6 Let's Start Simple 2.Remote-Controlled Car (RPA): This is the first step toward automation—tasks are easier but still require explicit instructions. Example: Now, the child gets a remote-controlled car. The car moves forward, backward, and turns based on buttons pressed on the remote control. The child doesn’t need to physically push the car anymore, but they still need to guide it. Characteristics: • The car follows commands given via the remote. • It performs repetitive actions but cannot think or adapt. • If an obstacle appears, the child must manually steer it around the obstacle using the remote. In the context of automation: The remote-controlled car represents RPA (Robotic Process Automation). RPA automates repetitive tasks but relies entirely on pre-programmed instructions and cannot handle anything outside of those instructions. Example in the real world: An RPA bot processing invoices by extracting data from fixed formats.
- 7. 7 Let's Start Simple 3.Autonomous Car (Agentic AI): This is the leap to intelligence and independence—no manual intervention is required. Example: The child now has an autonomous car. The car has sensors, a camera, and intelligence built in. If you tell the car, “Drive to the other side of the room,” it: • Perceives the environment (using its sensors to detect obstacles). • Plans the best route to reach the other side. • Acts by driving itself, adjusting the route in real-time if something unexpected appears (like a toy in its path). Characteristics: • The car works independently based on its understanding of the environment. • It adapts to changes and solves problems without needing explicit instructions. • It is goal-oriented: If its path is blocked, it recalculates and continues toward the goal. In the context of automation: The autonomous car represents Agentic AI. Agentic AI can perceive, plan, and act autonomously, making it capable of handling complex and dynamic scenarios. Example in the real world: An agentic AI system in business might handle customer complaints by analyzing emails, deciding the best response, and executing the required actions—without needing step-by-step guidance.
- 8. 8 Take Away Manual Car Entirelyhuman-driven—no automation at all. Everything dependent on Human and No Automation Remote-Controlled Car (RPA) Automates repetitive actions but requires explicit control and guidance. Actions are predefined Autonomous Car (Agentic AI) Fully independent, capable of perceiving, planning, and acting to achieve goals without constant human intervention.
- 9. 9 Who will Fetchthe Ball ? Imagine you’re playing in a park with a ball, and you accidentally kick it into the bushes.
- 10. 10 Who will Fetchthe Ball ? How Scout (Agentic AI) Works: 1. Understanding: Scout notices that the ball is missing and sees where it went. 2. Planning: It thinks, “The ball is in the bushes. I need to go around the bench and carefully pick it up.” 3. Action: Scout rolls over, avoids obstacles like a puddle and a rock, grabs the ball, and brings it back to you. Instead of you having to go fetch it, there’s a helpful robot called “Scout” You didn’t need to tell Scout step-by-step what to do. You simply said, “Scout, the ball is gone!” and it figured out everything else.
- 11. 11 Why Scout isAgentic AI? Perception It noticed the ball was gone and saw where it went. Planning It decided how to reach the ball, avoiding obstacles. Action It retrieved the ball and returned it to you and wait for next Instruction.
- 12. 12 Robotic Agentic The futureis both agentic and robotic. Left Brain Structured and logical, efficiency-oriented, systematic processing Right Brain Creative and intuitive, decision making and adaptability, handling ambiguity
- 13.
- 14.
- 15.
- 16.
- 17. UiPath GenAI Activities UiPathIntegration Service
- 18. 18 • The UiPathGenAI Activities package is an advanced feature set that empowers developers to integrate generative AI capabilities directly into automation workflows. • This package provides access to UiPath-managed large language models (LLMs) from multiple third-party providers, without requiring users to handle complex subscriptions or setups. What is UiPath GenAI Activities package
- 19. 19 UiPath GenAI Activities Activitiesmaking it easy to access, develop with, and leverage high qualityAI predictions in automation workflows. AI Trust Layer PII Filtering – Context Grounding UiPath GenAI Activities UiPath-managed LLMs Best-in-class Automation Core automation and integrated value across the platform including RPA, API, IDP, Test, PM 19
- 20. 20 UiPath Agent Catalog Predefinedtemplates to build and deploy agents more efficiently. Prebuilt Agents - designed and evaluated by UiPath for specific tasks with predefined prompt, tools, and escalations. Require minimum additional config to be executable. Agentic Workflow Templates - preconfigured Studio templates which invoke a Prebuilt Agent to complete a business process. Content Generation Email Generation Summarize Rewrite Language Translation Language Detection PII Detection Categorize Reformat Image Classification Object Detection Semantic Similarity Sentiment Analysis Named Entity Recognition Signature Comparison Compliance Monitoring Agent Continuously monitor operations and documentation to ensure compliance with industry regulations and internal policies. Risk Assessment Agent Evaluate operational risks by analyzing data from various sources, enabling the company to mitigate potential issues proactively. Web Search Agent Continuously monitor operations and documentation to ensure compliance with industry regulations and internal policies. Scorer Agent Evaluate and score decision options based on predefined criteria. Regulatory Reporting Agent Automates the compilation of reports required by regulatory bodies, ensuring accuracy and timely submission. GenAI Activities transforming into agents New, foundational prebuilt agents 20 Many more – coming soon!
- 21.
- 22.
- 23.
- 24.
- 25.
- 26.
- 27.
- 28. 28 Thank You Register foreach session here
- 29. 29 Register for nextlive session Transitioning to agentic automation