← Back to curriculum

Phase 11 · 17 lessons

LLM Engineering

Put LLMs to work in production.

01Prompt Engineering: Techniques & PatternsBuild 02Few-Shot, Chain-of-Thought, Tree-of-ThoughtBuild 03Structured Outputs: JSON, Schema Validation, Constrained DecodingBuild 04Embeddings & Vector RepresentationsBuild 05Context Engineering: Windows, Budgets, Memory, and RetrievalBuild 06RAG (Retrieval-Augmented Generation)Build 07Advanced RAG (Chunking, Reranking, Hybrid Search)Build 08Fine-Tuning with LoRA & QLoRABuild 09Function Calling & Tool UseBuild 10Evaluation & Testing LLM ApplicationsBuild 11Caching, Rate Limiting & Cost OptimizationBuild 12Guardrails, Safety & Content FilteringBuild 13Building a Production LLM ApplicationBuild 14Model Context Protocol (MCP)Build 15Prompt Caching and Context CachingBuild 16LangGraph — State Machines for AgentsBuild 17Agent Framework Tradeoffs — LangGraph vs CrewAI vs AutoGen vs AgnoLearn