Ask HN: 如何学习构建基于 Agent 的 AI 系统（如 Claude Code）

Hello folks,<p>I’m trying to learn how one can build agentic AI systems similar to Claude Code, and eventually adapt that knowledge toward domain-specific use cases (e.g., “Claude Code for healthcare, finance, education, etc.”).<p>For those of you who’ve studied or built these kinds of systems, I’d love to hear your recommendations on:<p>• Foundational learning: What books, courses, or papers provide the best grounding for understanding LLM-based systems and their decision-making?<p>• Architectural patterns: What design patterns are worth studying for things like context management, memory, reasoning, and orchestration?<p>• Build vs. deploy: How do you think about building internal systems vs. packaging&#x2F;distributing them as APIs, SDKs, or products?<p>• Open source projects: Which ones are most valuable to study for internals (decision making, evals, context engineering, tool use, etc.)?<p>• Evals and observability: What tools or products help evaluate quality, measure system behavior, and observe performance in real-world use?<p>• Models: Which models are best suited for “thinking” (reasoning, planning, decomposing problems) vs. “doing” (execution, coding, retrieval)?<p>• Learning path: How would you approach going from theory → prototype → production-quality system?<p>My goal is to discover high-quality resources that one can truly spend time learning from and building with—through iteration and practice—while also sharing what I learn so others on the same path can benefit.<p>Thanks in advance for sharing your experiences and guidance!