Create account and log in here

Home

Manage your account and visualize test results

Documentation to start your AI Quality Assurance

Supported chatbot uses cases. We constantly add more!

Define population of simulated AI personas

Instead of simulating conversation with AI personas, evaluate your own real historical conversations.

Evaluate the performance of your RAG chatbot: hallucinations, correctness, and answer relevance.

Define custom evaluation metrics to score each message in a conversation, and to flag and detect events.

To improve your models and even fine tune them.

Ask them questions to better understand their preferences and what could have been improved