← Interactive Guides
From tokens to agents
1 / 2
1. How LLMs work
Architecture · training · inference
2. How agents work
Harness · tools · RAG · context
← Previous
How LLMs work
How agents work →
Enable JavaScript to use this combined guide. It contains both chapters and all demos in one file: LLM architecture, parameters, quantization, training and inference; then agents, tools, skills, MCP, RAG and context.