document_assessment:
  path: "{file path or URL}"
  type: "{detected document type}"
  size: "{approximate size}"
  structure:
    has_sections: true|false
    has_lists: true|false
    has_tables: true|false
  quality:
    formal_language: true|false
    clear_requirements: true|false
    needs_interpretation: true|false

- "The system shall..."
- "The system must..."
- "Users should be able to..."
- "REQ-XXX:"
- Numbered requirements (1.1, 1.2, etc.)

- "When [trigger], the [system] shall [response]"
- "While [state], the [system] shall [behavior]"
- "Where [feature], the [system] shall [behavior]"
- "If [condition], then the [system] shall [response]"

- "It is important that..."
- "We need..."
- "The goal is to..."
- "Users expect..."
- "Performance should..."

extracted_requirement:
  id: REQ-{sequence}
  text: "{cleaned requirement statement}"
  source: document
  source_file: "{file path}"
  source_location: "{section/page/line}"
  original_text: "{exact text from document}"
  type: functional|non-functional|constraint|assumption
  confidence: high|medium|low
  extraction_method: explicit|pattern|inferred
  needs_review: true|false
  review_notes: "{why review needed}"

categories:
  functional:
    - features
    - behaviors
    - interactions
  non_functional:
    - performance
    - security
    - usability
    - reliability
    - scalability
  constraints:
    - technical
    - business
    - regulatory
  assumptions:
    - environmental
    - user_behavior
    - dependencies

deduplication:
  strategy: semantic_similarity
  threshold: 0.8
  action: merge|flag_for_review
  merged_requirements:
    - id: REQ-merged-001
      sources: [REQ-001, REQ-015]
      text: "{consolidated requirement}"

transcript_extraction:
  focus_on:
    - Action items
    - Decisions made
    - Requirements discussed
    - Concerns raised
  patterns:
    - "We decided that..."
    - "The requirement is..."
    - "Action item:"
    - "TODO:"
    - "Need to..."
  speaker_context:
    - Note who said what
    - Weight by speaker role

regulatory_extraction:
  focus_on:
    - Mandatory requirements ("shall", "must")
    - Prohibited actions ("shall not", "must not")
    - Conditional requirements ("if...then")
  compliance_mapping:
    - Reference section numbers
    - Note effective dates
    - Track version/revision

competitor_extraction:
  focus_on:
    - Feature descriptions
    - User capabilities
    - Unique selling points
  output:
    - Feature requirements
    - Differentiation opportunities
    - Gap identification
  confidence: low  # Based on external observation

legacy_extraction:
  focus_on:
    - Existing requirements
    - System behaviors
    - Integration points
  modernization:
    - Update terminology
    - Convert to EARS format
    - Flag deprecated requirements

extraction_result:
  source:
    file: "{path or URL}"
    type: "{document type}"
    extraction_date: "{ISO-8601}"
    confidence: high|medium|low

  statistics:
    total_candidates: {number}
    extracted: {number}
    filtered: {number}
    needs_review: {number}

  requirements:
    - id: REQ-{number}
      text: "{requirement}"
      type: functional|non-functional|constraint
      source_location: "{section/page}"
      confidence: high|medium|low
      original_text: "{exact source text}"

  review_items:
    - requirement_id: REQ-{number}
      reason: "{why review needed}"
      suggestion: "{proposed action}"

  metadata:
    sections_processed: {number}
    extraction_patterns_used: ["{pattern names}"]

guided_behavior:
  document_selection: Human selects
  extraction_strategy: AI suggests, human approves
  each_requirement: AI highlights, human confirms
  categorization: AI suggests, human validates

semi_auto_behavior:
  document_selection: AI suggests priority, human approves list
  extraction_strategy: AI chooses autonomously
  requirements: AI extracts all, human reviews in batches
  categorization: AI categorizes, human spot-checks

full_auto_behavior:
  document_selection: AI processes all relevant
  extraction_strategy: AI optimizes per document
  requirements: AI extracts, deduplicates, categorizes
  output: Full extraction report for final review

.requirements/{domain}/documents/DOC-{filename}-{timestamp}.yaml