my project:: [[Personal AI Agent -- Obsidian + Claude Code with Cursor Vibe]] > 1. They do the "context engineering" > 2. They orchestrate multiple LLM calls under the hood strung into increasingly more complex DAGs, carefully balancing performance and cost tradeoffs. > 3. They provide an application-specific GUI for the human in the loop > 4. They offer an "autonomy slider" Will the LLM labs capture all applications or are there green pastures for LLM apps? ([[只包装基础模型能力的垂类 specialized AI 没有未来]]) > "LLM labs will trend to graduate the generally capable college student, but LLM apps will organize, finetune and actually animate teams of them into deployed professionals in specific verticals by supplying private data, sensors and actuators and feedback loops." - **LLM companies** (OpenAI, Anthropic, etc.) → provide general-purpose AI capabilities - **"Cursor for X" apps** → take those capabilities and specialize them for specific industries/use cases with domain-specific data, tools, and workflows