Flashcard: name the three augmentation sub-decisions in a production RAG pipeline.

Attempt it

(1) Chunk ordering: where each retrieved chunk lands in the prompt (head/tail beats raw similarity order due to 'lost in the middle'). (2) System-prompt directives: explicit instructions to ground in context, cite chunks by number, and refuse if context is insufficient. (3) Citation tagging: numbering chunks so the LLM can emit verifiable attributions. None of these is reranking (that's retrieval), query embedding (retrieval setup), or fine-tuning (a different mechanism).

Your answer

Quick reference

TL;DR

The augmentation step is prompt construction: decide chunk ordering (head/tail, not raw similarity), write grounding and refusal directives, and tag chunks with numbers so the model can cite.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Imagine you hand a student an open book exam plus a stack of photocopied pages. Just dumping the pages on their desk isn't enough. You decide which pages go on top and bottom, because people skim the start and end and gloss over the middle of a thick pile. You write a sticky note saying 'only answer from these pages, and if they don't cover it, say so.' And you number every page so the student can write 'see page 3' next to each claim. Those three moves are exactly the augmentation step in RAG. Retrieval already found the pages; augmentation is how you arrange and frame them before the model reads. It is pure prompt engineering, and it often matters as much as which pages you fetched.

Key concepts

RAG system design Prompt engineering Chunking strategies

Quick scan · 2–4 min

Everything important, quickly.

3 min: define augmentation as prompt construction, then the three decisions (ordering with lost-in-the-middle, directives for grounding and refusal, citation tagging), plus the retrieval-vs-augmentation boundary.

Side-by-side

Stage	What it decides	Example concern
Retrieval	Which chunks to fetch	Hybrid search, reranking, top-k
Augmentation	How chunks enter the prompt	Ordering, directives, citation tags
Generation	How the model produces text	Model choice, temperature, decoding

Real-world examples

Real products, models, and research that use this idea.

Perplexity numbers its retrieved sources and instructs the model to cite each claim with a bracketed source index in the rendered answer.
Anthropic's Claude with the citations feature tags document chunks so responses carry verifiable references back to the supplied source.
OpenAI's file-search tool in the Responses API assembles retrieved file chunks into the prompt with source attribution metadata.
Glean enterprise search orders retrieved workspace chunks and instructs the model to ground answers strictly in permitted documents.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QHow would you decide chunk ordering when you have ten retrieved chunks and a long context window?

Sign in or go Pro to see the approach for this follow-up.

QWhat does a good refusal directive look like, and how do you test that the model actually obeys it?

Sign in or go Pro to see the approach for this follow-up.

QHow do you make citation tags survive from prompt assembly through to a clickable source in the UI?

Sign in or go Pro to see the approach for this follow-up.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.