Track-specific guidance 

 
Track 1: UiPath Maestro Case 

Focus on: 

  • dynamic, exception-heavy workflows 

  • coordination between agents, robots, and people 

  • human-in-the-loop decision making 

  • long-running business processes with full visibility and auditability 

Example: 

An insurance claims solution where cases progress through intake, investigation, approval, and settlement stages. AI agents classify claim types, robots gather policy data, human adjusters review edge cases, and Maestro orchestrates the entire lifecycle while maintaining transparency and accountability. 

Or a patient care coordination workflow where agents manage referrals, scheduling, document exchange, and follow-ups across multiple providers, while healthcare staff stay involved at critical decision points. 

Another example could be an HR onboarding process where each employee case moves through document collection, IT provisioning, training assignment, and manager approvals, with work dynamically routed based on role, location, or missing information. 

What strong submissions usually demonstrate: 

  • clear progression of work through stages or milestones 

  • intelligent handling of exceptions and edge cases 

  • meaningful collaboration between humans, agents, and automations 

  • visibility into case status, ownership, and outcomes 

  • orchestration of agents regardless of the framework they were built in 

  • clear auditability and visibility into how decisions were made 

Learn more: 

 

Track 2: UiPath Maestro BPMN 

Focus on: 

  • end-to-end process orchestration using BPMN 2.0 

  • coordination across humans, robots, APIs, and AI agents 

  • structured task routing, approvals, and decision flows 

  • process transparency, resiliency, and scalability 

Example: 

An order-to-cash workflow where RPA pulls orders from email, EDI, and portals, an agent normalizes line items and flags pricing exceptions, and Maestro BPMN orchestrates credit checks, inventory allocation, fulfillment, and invoicing across ERP and CRM in a defined sequence. A collections agent monitors aging invoices and escalates disputes to finance for review. 

Or a procure-to-pay process where agents parse requisition intent, recommend vendors, and route approvals based on budget thresholds and category rules, RPA handles PO creation and invoice ingestion across ERP and AP systems, and an invoice agent reconciles discrepancies between PO, receipt, and invoice — escalating only true exceptions to AP for human review. Maestro BPMN keeps the full flow coordinated from requisition to payment. 

What strong submissions usually demonstrate: 

  • a well-designed BPMN process with clear stages and ownership 

  • thoughtful orchestration between different actor types 

  • intelligent routing and decision-making logic 

  • reliable integrations across enterprise systems 

  • efficient handoffs that keep work moving smoothly from start to finish 

  • resilient orchestration that can recover from failures or delays 

Learn more: 

 

Track 3: UiPath Test Cloud 

Focus on:

  • reimagining how software testing is designed, automated, executed, and managed across modern enterprise environments
  • moving faster with more confidence by increasing coverage, improving reliability, and reducing the manual effort required to validate complex systems
  • building agents that evaluate requirements and turn them into meaningful test scenarios
  • identifying fragile or outdated tests before they slow down a release
  • recommending fixes when automation breaks
  • orchestrating the right tests at the right time based on risk, coverage, and change impact
  • validating AI-infused workflows, including third-party agents and AI services operating inside UiPath-orchestrated processes

Example:

A testing solution where AI agents analyze requirements and automatically generate meaningful test scenarios, prioritize regression coverage based on risk and change impact, execute tests against enterprise applications, and flag potential issues before deployment.

Or a framework where agents identify flaky or outdated tests, recommend fixes when automation breaks, and optimize execution schedules for maximum coverage — continuously adapting testing strategies based on recent changes and failures.

Another example could be validating third-party AI agents or external AI services operating inside a UiPath-orchestrated workflow, ensuring that outputs remain reliable, compliant, and production-ready before they impact real users or business systems.

What strong submissions usually demonstrate:

  • a clear vision for how agentic testing helps teams move faster with more confidence — not just automate existing test cases
  • measurable improvements in testing efficiency, coverage, or release confidence
  • intelligent use of agents to reduce manual effort across the testing lifecycle
  • resilient approaches for validating dynamic, AI-driven systems and workflows
  • quality as a continuous, intelligent, and governed capability — not a late-stage checkpoint
  • practical enterprise applicability and scalability of the testing approach

 

Learn more: 

 

Inspiration 

Explore real-world solutions and past projects: 

 

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. 

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.