- Getting started
- Installation
- Installing UI Agent
- Best practices
UI Agent user guide
Best practices
We recommend one of the following two clear paths to get started, depending on your context:
- Selectors that fail often.
- Automations that break after UI changes.
- Compelled to write overly complex logic for seemingly simple tasks.
If you start a UIAutomation from scratch, you can build it entirely using UI Agent with granularity.
Each UI Agent activity must correspond to a small, well-scoped step in your process, ideally two or three steps that naturally belong together.
This granular approach has the following benefits:
- Maximizes accuracy.
- Keeps the agent focused.
- Avoids overloading the model with too much context.
Depending on the complexity of each step, you can choose the appropriate AI model, balancing cost-efficiency and capability.
UI Agent is designed to excel at specific, high-friction points, also known as Controlled agency scenarios, representing small, critical areas of automation where traditional tools are most fragile. Rather than replacing entire workflows, UI Agent brings agentic execution to the parts that need it most.
UI Agent can help fix some of the following traditional UIAutomation issues, delivering improved resilience, smarter handling of complex interactions, and reduced maintenance and supported effort:
- Brittle selectors that break easily.
- Complex UI structures and dynamic elements.
- Hard-to-reach UI elements such as popups, virtualized lists, embedded tables, or custom controls.
