Find here everything you need to go successfully from idea → working agentic solution → final submission. 

 
Start here 

UiPath AgentHack is built around real, working agentic systems, not concepts or prototypes. 

You’ll design and ship a solution on the UiPath Platform that: 

  • coordinates multiple agents  

  • handles long-running processes  

  • handles failures, retries, and exception paths gracefully 

  • maintains visibility, auditability, and control across the workflow 

  • keeps humans in the loop at critical decision points  

To get started: 

  • Register on Devpost 

  • Ask for access on UiPath Labs here: Teams must designate a representative to complete the lab access form on behalf of the group.

  • Receive your UiPath Labs access (within 3 business days)  

  • Start building and running the solution in UiPath Automation Cloud (in the environment where you receive access for on email) 

New to agentic automation? Take a look here!

UiPath Platform overview 

What is UiPath Labs? 

UiPath Labs is the sandbox environment where you'll build, test, and run your AgentHack project. It comes pre-configured with the UiPath tools and services you need, so your team can focus on building, not setup. 

Core tools & technologies 

All solutions must run on the UiPath Automation Cloud. You can include Agent Builder, Maestro, API Workflows, coding agents, and RPA where needed. You're welcome to bring in agents built on external frameworks and LLMs, in fact, we encourage it. The point is that UiPath is the orchestration and governance layer that ties everything together. 

Agent Builder 

Build low-code AI agents that can reason, plan, and act. 
Primary tool for creating agents across all tracks. 
https://docs.uipath.com/agent-builder 

https://docs.uipath.com/agents/automation-cloud/latest/user-guide/building-an-agent-in-studio-web  

 UiPath Maestro 

The orchestration and governance layer coordinating agents, robots, APIs, and people – especially relevant for tracks 1&2. 

  • multiple agents  

  • APIs and systems  

  • robots and data  

  • human decision points  

Central to Multi-Agent Orchestration and Case Management scenarios. 
https://docs.uipath.com/maestro 

Explore relevant Maestro use cases, process areas, and supporting assets: Maestro Use Case Explorer 

API Workflows 

Connect your agents to external systems and services without managing infrastructure. 

Useful for:  

  • enterprise integrations  
  • ERP/CRM connectivity  
  • external AI services  

Coded Agents 

Coded Agents: use our Python SDK to build agents in code for maximum flexibility and custom logic. Combine your coded agent with low code UiPath components and external agent frameworks for the most versatile solutions. 
https://docs.uipath.com/studio/docs/coded-automation 

https://docs.uipath.com/agents/automation-cloud/latest/user-guide/about-coded-agents  

UiPath for Coding Agents (AI-assisted development) 

UiPath for Coding Agents is a platform-wide support for coding agents that enables AI development tools like Claude Code, OpenAI Codex, and Cursor to build, test, deploy, operate, and govern UiPath automations end-to-end, through a CLI and agent skills. 
*Solutions using coding agents receive bonus points. 

Unified Builder Canvas: the development environment that brings low-code and code-first development together in one place. 

Document Understanding (IDP) 

Extract and process data from: 

  • PDFs  

  • forms  

  • images  

*Especially useful for: 

External agent frameworks 

You are encouraged to integrate external agents: 

  • and others  

*UiPath acts as the orchestration and governance layer across all agents. 

 

Learning resources 

Whether you're new or experienced, use these resources to ramp up quickly. 

Getting started 
Go deeper 
Webinars & office hours 

Throughout the 7-week hackathon, you’ll have access to live sessions designed to help you go from idea to submission. 

Webinars 

Deep dives into: 

  • Agent Builder  

  • Maestro orchestration  

  • Track-specific patterns  

 

Note! The best submissions solve real business problems, not abstract ideas. Also – the strongest solutions use agents autonomously where appropriate, while ensuring humans remain accountable for high-impact decisions. 

Optional: You can also fill in a short form related to your feedback about the UiPath products you used. This helps us gather feedback to improve UiPath products and gives you/your team the chance to win the Best Product Feedback award ($1500). This award goes to the individual/team that provides the most insightful, relevant, and high-impact feedback on UiPath Maestro, UiPath Maestro BPMN, UiPath Test Cloud, or any UiPath tools/platforms used during the hackathon. Only one representative of the team needs to fill in the survey after gathering feedback from all members of the team.

During UiPath AgentHack, participants may be provided with training resources, development materials, or other information that is proprietary to UiPath. By participating, you agree to treat any such information as confidential and not to use it for purposes outside of this hackathon. At the end of the hackathon, participants are required to return or destroy any confidential information received from UiPath, and to certify such destruction upon request. This obligation survives for three years after the end of the hackathon, except for information protected as trade secrets, which remains confidential indefinitely.

For full details, please refer to Section 12 (Confidentiality) of the Official Rules.