AgentHack submission type
Enterprise Agents
Name
Utkarsh Khandelwal
Team name
AutoBot
Team members
@raghavbidani @myselfrahul456 @er.utkarsh.khandelwal
How many agents do you use
Multiple agents
Industry category in which use case would best fit in (Select up to 2 industries)
Information technology and services
Complexity level
Intermediate
Summary (abstract)
RPA developers currently spend significant manual effort on repetitive setup tasks at the start of every project, such as:
• Effort estimation using static templates
• Flowchart creation from plain-language process descriptions
• Manual development of Dispatcher/Performer workflows in REFramework
• Configuration of Queues, Assets, and Triggers in Orchestrator
• Deployment of packages and creation of Runbook documentation
While some basic automation exists (macros, prompt-based generation), these are siloed, static, and require human oversight, with no true autonomy or adaptive behaviour. This results in slow delivery, error-prone setup, and limited scalability.
Detailed problem statement
RPA developers currently spend significant manual effort on repetitive setup tasks at the start of every project, such as:
• Effort estimation using static templates
• Flowchart creation from plain-language process descriptions
• Manual development of Dispatcher/Performer workflows in REFramework
• Configuration of Queues, Assets, and Triggers in Orchestrator
• Deployment of packages and creation of Runbook documentation
While some basic automation exists (macros, prompt-based generation), these are siloed, static, and require human oversight, with no true autonomy or adaptive behaviour. This results in slow delivery, error-prone setup, and limited scalability.
Challenges
• Time-consuming and error-prone initial setup
• Developers consumed by boilerplate instead of innovation
• No intelligent or decision-making capabilities in current tooling
• Inability to scale automation efficiently across the enterprise
Detailed solution
Solution – Agentic Autobot
Agentic Autobot is a first-of-its-kind AI-powered solution that brings autonomous agentic intelligence into the RPA development lifecycle. It introduces specialized UiPath agents that automate every stage of the RPA SDLC, transforming a manual, step-by-step process into a seamless, intelligent pipeline.
Key intelligent agents include:
• 
Designer Agent – Understands process descriptions and auto-generates design blueprints and flowcharts.
• 
Estimation Agent – Calculates effort, cost, and complexity with AI-based analysis.
• 
Development Agent – Builds Dispatcher/Performer workflows in REFramework using reusable components and best practices.
• 
Deployment Agent – Automatically configures Orchestrator assets, queues, triggers, and environments.
• 
Publish Agent – Handles package publishing and versioning to orchestrator or repositories.
• 
Document Agent – Auto-generates detailed technical documentation and runbooks.
This solution will empower RPA developers to focus solely on complex business logic and core problem-solving by autonomously handling repetitive setup, configuration, and initial coding tasks, thereby significantly accelerating the RPA development lifecycle and ensuring consistent quality.
Demo Video
Expected impact of this automation
•Time Efficiency: Reduces project setup time by 80%.
•Standardization : Ensures consistent RE-Framework structure and naming conventions.
•Developer Friendly : Enables developers to focus on core logic instead of boilerplate.
•Testing & Validation : Automatically creates test cases and validates deployments.
•Scalable : Makes onboarding and scaling RPA projects faster and uniform. •Smart triage : using LLM-based understanding of requirements and available environment.
UiPath products used (select up to 4 items)
UiPath Agent Builder
UiPath Assistant
UiPath Automation Cloud™
UiPath Autopilot™
UiPath Coded Agents
UiPath Orchestrator
UiPath Robots
UiPath Studio
UiPath Studio Web
Integration with external technologies
OpenAI, Kroki API
Agentic solution architecture (file size up to 4 MB)
Sample inputs and outputs for solution execution
A config file which is to be placed at the local folder which has flags for various features and you can turn then on and off using the config file.
The config file is placed on the google drive and link shared.