Building open source agents for software testing
Modern test automation tools face two key challenges 🧩:
- Complexity: Non-technical teams struggle with existing tools.
- Maintenance: Traditional test execution lacks intelligent state based execution and interactions.
These inefficiencies delay releases, increase costs, and reduce software quality.
Hercules, an open-source project by TestZeus, redefines end-to-end testing by leveraging AI agents to:
- Execute natural language tests
- Interact with browsers, APIs, or other interfaces
- Bid adieu to automation maintenance, as we see how multi agentic systems “REAct” to the application at hand.
This presentation will showcase how Hercules tackles core testing challenges, its value to the software development lifecycle, and its impact on the modern testing landscape.
🚀 About Hercules: world’s first open source end to end testing agent
Hercules is the world’s first open-source testing agent, built to handle the toughest testing tasks so you don’t have to. It turns simple, easy-to-write Gherkin steps into fully automated end to end tests—no coding skills needed. Whether you’re working with tricky platforms like Salesforce or running tests in your CI/CD pipeline, Hercules adapts to your needs and takes care of the details. With Hercules, testers can perform UI/API/Accessibility/Security/Mobile and Visual testing. All of this thanks to a multi agentic framework under the hood.
In this session , we will pop the hood, and see how this multiagentic solution works by utilizing a small army of agents like Browser agent, API agent, etc. and tools like Playwright to ensure that the user can tackle the most herculean tasks of test automation.
🎯 Key takeaways for the audience
- Warm introduction to multi-agentic architectures.
- Notes on cost and prompt optimization
- Deploying agents to production and “gotchas”
- Building in Open Source and Building for Extensibility.
🎯 Target audience
- Testers
- Developers
- QA Managers
- AI/ML Practitioners
- Open-source Enthusiasts