All activity
Devansh Tandonleft a comment
This is incredible! I've worked on similar tools for DeepMind & YouTube. How much control do users have over personas? Can I effectively write 'system prompts' to configure different personas & then have them test AI agents? For example, I want to make my agent safe to deploy to teens – want to create a number of teen & teen-risk related personas to red team the agent. From the website/demo...
SnowglobeSimulate real users to test your AI before launch