Skip to slide
065 / 221

CH 05 · Context Engineering and Memory · 05/18

Read as one page

Reference, don't embed

A powerful pattern for document- or data-heavy agents: don't dump content into context; reference it and let the model pull what it needs via tools. Instead of pasting five documents into the prompt, give the model short handles ("doc-0", "doc-1") and a read_document tool. The model reads only what the task requires.

This has three benefits:

  1. Smaller prompts: you pay for content only when it's actually used.
  2. Forced grounding: the model must explicitly fetch content, which makes it engage with the real text rather than half-remembered training data.
  3. Freshness: referencing always pulls the current version, avoiding stale content (see below).

Use short, stable, human-meaningless-but-model-friendly labels for the handles, assigned deterministically, so the model can reference them reliably and can only reference things that actually exist.

Finished this idea?

Your learning progress stays in this browser.