32dots HEIDELBERG AI

Context Engineering

What the AI sees matters more than how you ask

The sequel to prompt engineering: managing what information goes into the model's window and how it's structured. Organised by the Write · Select · Compress · Isolate framework, with anti-pattern → done-right examples that tie into RAG (Dify) and agents (n8n).

After this chapter you can
Decide what to put in the context window — and what to leave out
Use retrieval (RAG) to pull only the relevant context
Compress long histories and prune noise to fight context rot
Isolate concerns across steps and agents for clean context
Write What you put in the window
Give it the source, not just the question Don't ask the model to recall a specific paper from memory — put the actual text in front of it.
What does the 2023 Zhang paper say about CRISPR off-target effects?
Paste the paper text (or attach the PDF) and ask: "Using only this paper, summarize what it reports about off-target effects."
Why it works: A model cannot reliably recall one specific paper from training. Give it the real text and it answers from fact, not a fuzzy memory.
Instructions at the right altitude Not a brittle 2-page rulebook, not a vague one-liner — a handful of strong heuristics.
Be a helpful research assistant. —or— a 2-page list of every edge case and rule.
You are a research assistant for biology students. Be concise, define jargon on first use, prefer primary sources, and say when you are unsure.
Why it works: Over-specified prompts get brittle and hard to maintain; vague ones get generic. A few clear principles steer behavior without micromanaging.
Put key info where the model looks Models attend most to the start and end of the context — not the middle.
Bury the actual task in the middle of three pages of pasted material.
Instruction at the top, the data clearly tagged in the middle, and restate the ask at the end: "Remember: answer only from the text above."
Why it works: Important instructions buried in a long middle get lost ("lost in the middle"). Anchor them at the edges.