liveBook · Manning

System prompt

As explained in Retrieval Augmented Generation, The Foundational Ideas

A system prompt is a high-priority instruction context that establishes a language model's behavior and constraints.

A system prompt establishes the model’s operating behavior before it performs a task. In retrieval systems, it can shift query generation from shallow paraphrasing toward deliberate coverage of different facets and sub-intents, improving recall without changing the retriever itself. section 8.2

Effective system prompts make the intended behavior explicit:

  • Specify the task and the dimensions to cover, such as distinct facets, sub-intents, or interpretations. section 8.2
  • Preserve domain-critical details by naming what to extract, what to omit, and which terms or relationships require exact wording. section 10.6
  • Define evaluation criteria and explicit reasoning steps when the prompt governs an evaluator rather than a generator. section 14.3.1

From vague rewriting to facet coverage

For “What is the best laptop for college?”, a weak prompt produces near-duplicate rewrites. A stronger system prompt requests distinct angles, yielding queries about durability, portability, price, and battery life. Each query can retrieve a different document set, widening coverage while remaining tied to the original intent. section 8.2

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Explains prompt design through task criteria, reasoning steps, domain constraints, and output formats, but not model training.
Examples
Uses laptop facet queries, technical-documentation extraction rules, legal-clause preservation rules, and faithfulness-evaluation instructions.
What it assumes
Assumes familiarity with language-model tasks and retrieval or evaluation pipelines, while teaching how prompts specify behavior from task requirements.
What you can do after
Apply it via structured prompts that broaden retrieval coverage, preserve domain details, or standardize evaluation behavior.
How it connects
Connects to query generation, retrieval, summarization, chain-of-thought, and evaluation.

Also explained in

Compare how 3 books explain system prompt →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Retrieval Augmented Generation, The Foundational Ideas. The section links point to the parts of the book it draws on.