Phase 11
LLM Engineering
Put LLMs to work in production applications.
Lessons (17)
- 01Prompt Engineering: Techniques & Patterns
- 02Few-Shot, Chain-of-Thought, Tree-of-Thought
- 03Structured Outputs: JSON, Schema Validation, Constrained Decoding
- 04Embeddings & Vector Representations
- 05Context Engineering: Windows, Budgets, Memory, and Retrieval
- 06RAG (Retrieval-Augmented Generation)
- 07Advanced RAG (Chunking, Reranking, Hybrid Search)
- 08Fine-Tuning with LoRA & QLoRA
- 09Function Calling & Tool Use
- 10Evaluation & Testing LLM Applications
- 11Caching, Rate Limiting & Cost Optimization
- 12Guardrails, Safety & Content Filtering
- 13Building a Production LLM Application
- 14Model Context Protocol (MCP)
- 15Prompt Caching and Context Caching
- 16Agent State Machines — Graphs, Nodes, Checkpoints
- 17Agent Framework Tradeoffs — Graph, Role, and Actor Orchestration