Phase 11
LLM Engineering
Phase 11: LLM Engineering. 17 hands-on lessons building AI from first principles in the browser. Free reading; graded exercises and certificate with lifetime access.
- Prompt Engineering: Techniques & Patterns (graded)
- Few-Shot, Chain-of-Thought, Tree-of-Thought (graded)
- Structured Outputs: JSON, Schema Validation, Constrained Decoding (graded)
- Embeddings & Vector Representations (graded)
- Context Engineering: Windows, Budgets, Memory, and Retrieval (graded)
- RAG (Retrieval-Augmented Generation) (graded)
- Advanced RAG (Chunking, Reranking, Hybrid Search) (graded)
- Fine-Tuning with LoRA & QLoRA
- Function Calling & Tool Use (graded)
- Evaluation & Testing LLM Applications (graded)
- Caching, Rate Limiting & Cost Optimization (graded)
- Guardrails, Safety & Content Filtering (graded)
- Building a Production LLM Application
- Model Context Protocol (MCP)
- Prompt Caching and Context Caching
- LangGraph — State Machines for Agents
- Agent Framework Tradeoffs — LangGraph vs CrewAI vs AutoGen vs Agno