ai-native-developmentlisted

# AI-Native Development ## Core Concepts ### Embeddings & Vector Search See `${CLAUDE_SKILL_DIR}/references/vector-databases.md` for embeddings setup, cosine similarity, chunking strategies, and vector database guides (Pinecone, Chroma, Weaviate, Qdrant). ### RAG (Retrieval-Augmented Generation) See `${CLAUDE_SKILL_DIR}/references/rag-patterns.md` for basic and advanced RAG patterns, citation strategies, hybrid search with Reciprocal Rank Fusion, conversation memory patterns, and error handling. ### Function Calling & Tool Use See `${CLAUDE_SKILL_DIR}/references/function-calling.md` for tool definition patterns (OpenAI and Anthropic), function calling loops, parallel and streaming tool execution, input validation with Zod, and error handling. ### Agentic Workflows Enable LLMs to reason, plan, and take autonomous actions. **Patterns:** - **ReAct**: Reasoning + Acting loop with observations - **Tree of Thoughts**: Explore multiple reasoning paths - **Multi-Agent**: Specialized agents collaborating on complex tasks - **Autonomous Agents**: Self-directed goal achievement - **ML Experiment Loops**: Autonomous iteration on ML metrics using /experiment for hyperparameter tuning, evaluation improvement, and model selection. See `${CLAUDE_SKILL_DIR}/references/ml-experiment-loops.md` for patterns and worked examples. **Detailed Implementation:** See `${CLAUDE_SKILL_DIR}/references/agentic-workflows.md` for: - Complete ReAct loop implementation - Tree of Thoughts exploration