{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/0ed2e16d43504661908adf201f8187ba\" frameborder=\"0\" width=\"1152\" height=\"864\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":864,"width":1152,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":864,"thumbnail_width":1152,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/0ed2e16d43504661908adf201f8187ba-ddeb678d321d1f76.gif","duration":603.862,"title":"Memorang mini by Aashni!","description":"In this video, I walk you through the process of creating and testing custom graders for our movie dataset using an LLM style grader called IMDBX, which checks if a given actor is in a movie. I demonstrate how to run multiple graders simultaneously, including numeric tolerance and non-null checks, and share the outcomes of these tests. I also highlight the importance of detailed feedback from the LLM, which helps us understand why certain tests pass or fail. I encourage you to think about potential improvements, such as optimizing the API call process. I'm looking forward to discussing any questions you might have about the architectural and product decisions I've made."}