{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/644b73ea68e34ded81a490c82a4cb99f\" 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/644b73ea68e34ded81a490c82a4cb99f-60998eb67bfa2b12.gif","duration":312.599,"title":"AzureDevopsForager","description":"This Loom demonstrates a hybrid AI search engine that answers questions and finds exact code identifiers within a codebase. Dan Weaver shows that semantic search can correctly infer the intended email sender class from plain-English input and that ranked results reflect class characteristics. He then illustrates exact string search by finding the iCatalog item service interface and the cached item catalog service as a related second result. Finally, he asks directly how the basket total is calculated and shows the underlying formula and sources in the code, noting that embeddings reside inside an Azure or Microsoft SQL database vector native type."}