TechPrep

Building blocks

How LLM features fail, context engineering, RAG end to end, and tool use with MCP.

Lessons

  1. 01How LLM features failA working mental model of tokens, context and sampling, organised around the ways production features break.
  2. 02Prompt and context engineeringTreat the context window as a budget you assemble per request: instructions, examples, retrieved data and state, each earning its tokens.
  3. 03Retrieval-augmented generation, end to endIngest, chunk, embed, retrieve, rerank, generate with citations, and evaluate retrieval separately from generation.
  4. 04Tool use, function calling and MCPGive the model typed tools, validate every call, and keep side effects behind permissions you would grant a junior engineer.