{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/92da8e57583b406a9c9dc310df5f9cfd\" 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/92da8e57583b406a9c9dc310df5f9cfd-f6cf3ac8f27a05eb.gif","duration":272.854,"title":"Using Prompt Attribute Clustering in OpenLens","description":"This Loom demonstrates how to use Prompt Attribute Clustering and filtering in OpenLens. It explains that each prompt can have multiple attributes, such as branded or language tags, and that you can add custom attributes like engine characteristics either in the prompts tab or via settings. Using the attribute filters, the author shows visibility changes for subsets, including 72.3 percent for prompts mentioning Ferrari and an overall 68.1 percent. It also covers filter logic like “Italian or English” versus “Italian and English” returning none, plus a hide feature to view non-branded prompts where visibility drops to about 60 percent."}