Prompt Engineering Context Requirements

Package Product Requirements — Shall Means Shall

Requirements language is normative: shall binds, should suggests, may permits. Package the spec so the distinction survives the AI's reading.

Overview

Requirements documents fail in AI hands when normative language flattens: "shall" and "should" blur into "the system does", and a binding requirement becomes a suggestion in the summary. The requirements type adds the rules that keep the hierarchy: shall/must statements are binding, should/may are weaker and stay distinguishable, and requirement identifiers (R1, R2…) become the citation unit. Paired with documentation mode's exact-quoting discipline, the package turns a spec into something the model reads like an engineer. This setup loads an export-feature spec with acceptance criteria.

Workflow

  1. Keep the language normative

    Shall binds, should suggests — the type rules state it so the reading preserves it.

  2. Cite by identifier

    R1, R2 become the unit of reference; "the spec says" becomes "R3 requires".

  3. Check designs against it

    The task frames the package: evaluate what I describe against these requirements.

Why This Works

  • Preserved normativity keeps binding requirements binding
  • Identifier citations make compliance claims checkable
  • Exact-quote discipline stops paraphrase from weakening requirements

Best for

  • PRDs and formal requirement documents
  • Design reviews against written requirements
  • Compliance-adjacent specification work

Not for

  • Writing the requirements document itself — that's the Markdown Output Builder's PRD mode
  • Extracting requirements into structured fields — the Extraction Prompt Generator

Use cases

  • Checking designs against a requirements spec
  • Keeping binding and optional requirements distinct
  • Citing requirements by their R-numbers

Tip: Save time by exploring related resources and tools that integrate with this workflow.

Explore all resources