C.W.K.
Stream
Lesson 10 of 10 · published

The Prompt Is Smaller Than the Context

~12 min · context, prompt-vs-context, mental-model

Level 0Apprentice
0 XP0/100 lessons0/14 achievements
0/120 XP to next level120 XP to go0% complete

Most of what you send is not your prompt

By 2026 the typical production request looks like: 200 tokens of system prompt, 50 tokens of user message, and 30,000 tokens of context (RAG results, conversation history, tool definitions). The instructions are 1% of what the model is reading. "Prompt engineering" is misnamed; most of the work is context engineering.

What this changes

  • The leverage moves from "better instructions" to "better context selection."
  • The error budget moves from prompt phrasing to chunk relevance.
  • The cost budget moves from output to input — output is small, input is huge.
  • The eval shape changes — you have to measure retrieval, not just LLM output.

The full-system view

Everything in this track — chunking, retrieval, reranking, citations, caching, compression, ordering — is part of the prompt now. A junior writes the instruction; a senior shapes the context.

Code

Where the tokens go (typical prod request)·plaintext
system prompt        :   200 tokens (1%)
user message         :    50 tokens (<1%)
tool definitions     :   400 tokens (1%)
conversation history : 2,000 tokens (7%)
RAG context          :27,000 tokens (90%)
----------------------------
total input          :29,650 tokens

External links

Exercise

Profile one of your production prompts: how many tokens go to system / instructions / user / tools / context? Identify the largest bucket and one experiment that would meaningfully reduce it.

Progress

Progress is local-only — sign in to sync across devices.
Spotted a bug or have feedback on this page?Report an Issue

Comments 0

🔔 Reply notifications (sign in)
Sign inPlease sign in to comment.

No comments yet — be the first.