<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/a6689ee47a7648beb682a4face8c3c3d&quot; frameborder=&quot;0&quot; width=&quot;1658&quot; height=&quot;1243&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1243</height><width>1658</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1243</thumbnail_height><thumbnail_width>1658</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/a6689ee47a7648beb682a4face8c3c3d-255f8ae2ae25ea93.gif</thumbnail_url><duration>814.827</duration><title>Using Perplexity to Check Survey Consistency</title><description>This Loom demonstrates how to use Perplexity projects to check inconsistencies between survey answers and the supporting narrative. The author runs an Editing project that identifies mismatches such as a greeting question marked N A when it should be A, and reward questions marked yes even when not mentioned in the narrative, then discusses refining prompts (for example, focusing on negative answers needing backup). They show how to create and edit the project instructions, and iteratively rerun checks to improve accuracy on specific questions like number 25. The video emphasizes tweaking prompt instructions until the results align with the survey content.</description></oembed>