{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/417ee03eb3a64ecbb132f0c94c6f65fa\" frameborder=\"0\" width=\"1728\" height=\"1296\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1296,"width":1728,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1296,"thumbnail_width":1728,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/417ee03eb3a64ecbb132f0c94c6f65fa-a6c4004903b668bf.gif","duration":298.755,"title":"Building a LinkedIn POV Content Agent","description":"This Loom explains how the creator built and demoed a LinkedIn POV agent to automate and standardize content research, writing, and publishing. They describe an architecture based on LandGraft that manages research state and separates prompts and schemas, plus a base tone document and an audience specific tone document for mid-complexity users. The agent is deployed as a web app in Streamlit and Railway, with runs traced in Langsmith to debug failures. In the demo, the agent takes about 5 to 10 minutes to run, produces an article on the average state of AI competency among working professionals, and provides a downloadable zip file containing the finished article, an iteration brief, and all research documents."}