Learn how to use Galtea’s Conversation Simulator to test your AI with a synthetic user.
1. Implement Your Agent
Agent
class with your conversational AI logic. Your agent receives the full conversation state and must return a response for each turn.2. Prepare Scenario Data
3. Create a Test and Sessions
4. Run the Simulator with Your Agent
SimulatorService.simulate()
to execute the conversation between your agent and the synthetic user, for each session.5. Evaluate the Results
evaluation_tasks.create()
.galtea.Agent
. Your agent should implement the call
method, which receives an AgentInput
(including conversation history and context) and returns an AgentResponse
.
conversation_scenarios.csv
) with your scenario data: