video1.0<iframe src="https://www.loom.com/embed/1cd6554ed9bb425aa1f2d71631997cf4" frameborder="0" width="1280" height="960" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>9601280Loomhttps://www.loom.com9601280https://cdn.loom.com/sessions/thumbnails/1cd6554ed9bb425aa1f2d71631997cf4-ad7f67d82627232e.gif280.311In my Loom I presented Docs, the Data Professionals Advisor, an interactive chatbot that answers only relevant questions and cites the right PDF or cheat sheet when it uses data. I shared how Docs was built using GPT 4.1 mini, a vector database with Agno, Gradio as the user interface, and Hugging Face for deployment, plus why I chose 4.1 mini for cost effectiveness and quality. I showed it at work, including expanding and downloading the cited PDF. I also asked for viewer feedback using the Helpful or Not helpful buttons, which get saved in logs. Finally, I reviewed the flow architecture, key lessons, and next steps.