{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Contextually Aware","title":"Context Engineering: What Every PM Building AI Needs to Know","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/07a139e1\"></iframe>","width":"100%","height":180,"duration":571,"description":"The best prompt engineer I know told me he stopped writing prompts.\nHe said: \"Prompts are maybe 5% of what makes AI actually useful. The other 95%? It's everything the model sees before you even ask a question.\"\nIf you're building AI features and still obsessing over prompt wording, you're optimizing the wrong thing.\nIn this episode, I break down context engineering—what it is, where the term comes from, and how product managers can own the context window without writing code.\n**What you'll learn:**\n- Why \"know your user\" is the foundation of context engineering\n- The 3 types of retrieval: keyword, semantic, and graph RAG\n- Why more context actually hurts performance (context rot)\n- How to build evals that learn from future outcomes\n- 5 actionable homework items you can start today\n**People mentioned:**\n- Simon Willison (AI Engineer, Creator of Datasette)\n- Kevin Weil (CPO at OpenAI)\n**Key terms:**\n- Context window\n- RAG (Retrieval Augmented Generation)\n- Semantic search / Vector databases\n- Graph RAG / Knowledge graphs\n- Context rot\n- Evals / Data flywheel\nContext engineering is where product strategy meets model behavior. The best AI products aren't using better models—they're using better context.","thumbnail_url":"https://img.transistorcdn.com/mOIectisCbUyi7hIoQ_1h3GrJqmEh2DnxOkLN3ooLJY/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9hMzNm/MDlmMGIyM2FjZTNl/N2Q5MWM0N2ZhZmFl/MDY2OC5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}