{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"ViBe","title":"The Cold Start Problem: How to Give a New AI Agent Enough to Work With","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/b013498f\"></iframe>","width":"100%","height":180,"duration":301,"description":"A new AI agent with perfect instructions can still produce outputs that feel completely generic — because capability without context isn't enough. This episode breaks down the three-layer cold start process that gives agents the institutional memory to actually work like your business.","thumbnail_url":"https://img.transistorcdn.com/rMP37Bpr_hCFtrDvjYFC2_5qcAUOOwHV-k1ISqqr94Q/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9kODFk/Y2UyZWExY2NhZTFm/ZjBkOTRmOWMzNzk5/ODU4MS5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}