{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/d08c5b76fc00468785fcdd9af516d241\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/d08c5b76fc00468785fcdd9af516d241-11a1bae61964896a.gif","duration":349.942,"title":"Exploring LineGraph Studio: Agent Testing and Helpfulness Checks 🚀","description":"In this video, I experimented with the LineGraph Studio using two different agents: a simple agent that provides direct responses and a helpfulness agent that checks the quality of its answers. I demonstrated how the simple agent responds to queries, like the current Bitcoin price, by invoking a Tably search and returning results based on scores. The helpfulness agent, on the other hand, loops through iterations to refine its answers if the initial response is deemed unhelpful. I also discussed the possibility of introducing interrupts to enhance the interaction flow. I encourage you to explore these features and consider how they might improve our processes."}