henryhawke AI & LLM Development
When to use
- Build LLM-powered applications
- Implement RAG (Retrieval-Augmented Generation)
- Design and optimize prompts
- Build AI agents and tool-using systems
- Set up vector databases and embeddings
- Evaluate LLM outputs
RAG architecture
- Document chunking strategies
- Embedding model selection
- Vector database setup (Pinecone, Weaviate, pgvector)
- Hybrid search (vector + keyword)
- Re-ranking and relevance tuning
Prompt engineering
- Chain-of-thought reasoning
- Few-shot and zero-shot patterns
- Constitutional AI techniques
- System prompt design
- Output formatting and validation
Agent patterns
- Tool-using agents
- Multi-agent orchestration
- Memory and context management
- LangChain/LangGraph architecture
- Evaluation frameworks