LEARNING PATH · AI Engineering

Master Context Engineering

For engineers whose agents forget, ramble, or blow the window.

Intermediate ~3h 45m9 lessons13 steps

The discipline that replaced prompt-tweaking, learned end to end: tokens and budgets, the four operations (write, select, compress, isolate), compaction and memory, cache-aware prompts — threaded through the handbook, labs, tools, papers and system designs.

  • Treat the context window as a budget and spend it deliberately
  • Apply write / select / compress / isolate to any overflowing agent
  • Design compaction, memory and just-in-time retrieval that keep long tasks coherent
  • Order prompts so caching slashes latency and cost
0 / 9 done · 0%
  1. HandbookNext up

    The Context Engineering Handbook

    The whole discipline in one sitting — read this first, revisit last.

  2. Lab

    The Tokenizer

    What a token actually is — watch BPE build them.

  3. ToolTool · optional

    Token Counter

    Measure a real prompt: tokens, cost, window fit.

  4. ToolTool · optional

    Context Window Visualizer

    Watch system prompt, tools, history and RAG fight for one budget.

  5. ToolTool · optional

    Context Budget & Cost Planner

    Price the window — what every extra segment costs.

  6. Challenge

    Trim History to a Token Budget

    Implement the compress operation under a hard budget.

  7. Handbook

    The RAG Handbook

    Select: retrieval is how the right knowledge enters the window.

  8. ToolTool · optional

    RAG Chunking Playground

    Tune chunk size and feel the precision/noise tradeoff.

  9. AI System Design

    Design an Agent Memory System

    Write: persist state outside the window, recall it on demand.

  10. Paper Breakdown

    MemGPT

    The OS view — context as RAM, storage as disk, the model as memory manager.

  11. Handbook

    The Agent Skills Handbook

    Isolate expertise: progressive disclosure, productized.

  12. Handbook

    The Loop Engineering Handbook

    When the loop compacts, spawns sub-agents, and re-reads notes.

  13. AI System Design

    Design ChatGPT

    Context engineering at planet scale — rebuilt every turn, cached by prefix.

Models stopped being the bottleneck; what you feed them became it. This path takes you from "what is a token" to designing the memory architecture of a long-running agent — the full context-engineering curriculum, in the order the ideas actually build on each other.

You start by making the budget tangible (tokenizer, counter, visualizer), then learn the four operations from the handbook, then go hands-on with each: trimming under a budget, selecting via retrieval and chunking, persisting with memory systems, and isolating with skills and sub-agent patterns. It ends at planet scale — how ChatGPT itself rebuilds context every single turn.

← All learning paths