Agents for testing

Agents offer capabilities powered by technologies like large language models (LLMs), machine learning, and traditional enterprise automation, agents are designed to operate in dynamic, non-deterministic environments. They can plan, act, learn, and adapt which makes them ideal for processes that require judgement, flexibility, and contextual awareness.

To start using agentic testing, build agents using the following core components:

• Prompts: Define natural language prompt with goals, roles, variables, and constraints. Prompts can be user-driven or system-generated.
• Context: Information sources the agent uses to ground decisions, such as memory, knowledge bases, or previous interactions.
• Tools: Actions the agent can take: invoking automations, using APIs, triggering microservices, or collaborating with other agents and robots.
• Escalations: Human-in-the-loop mechanisms, like Action Center or messaging channels, that enable review, approval, or assistance when needed. You can use action apps for creating escalations.

Additionally, you can use agent evaluations to make sure your agents perform as expected. Evaluations show if your agent performs well or needs refinement.

For more information on building native, low-code agents, or coded, external agents, visit Agent capabilities in the UiPath Platform.