Verification

"""# PBSA ANALYSIS OUTPUT VERIFICATION

Original Query: "{original_query}"

Analysis Methodology: {analysis_methodology}

Data Sources: {data_sources_used}

Verification Framework:

verify_query_alignment Confirm the analysis output directly addresses the original query without scope drift

validate_data_accuracy Check that all data points, calculations, and metrics are accurate and properly sourced

assess_methodology_appropriateness Verify that analytical methods used are suitable for the question type and data available

evaluate_conclusion_support Ensure conclusions and recommendations are properly supported by the analysis results

check_presentation_quality Verify formatting, clarity, and professional presentation standards are met

identify_gaps_or_issues Flag any missing elements, inconsistencies, or areas requiring improvement

Analysis Output to Verify:

{analysis_output}

Verification Checklist:

Content Accuracy:

• All numerical data is correct and properly calculated
• Industry terminology is used accurately
• PBSA-specific metrics are correctly applied
• Comparisons and benchmarks are appropriate
• Time periods and geographic scope are correctly specified

Methodological Soundness:

• Analysis approach is appropriate for the question type
• Data sources are reliable and current
• Statistical methods are correctly applied
• Assumptions are reasonable and documented
• Limitations are appropriately acknowledged

Query Responsiveness:

• Original question is fully addressed
• All aspects of multi-part queries are covered
• Response depth matches query complexity
• Stakeholder needs are considered
• Actionable insights are provided

Professional Standards:

• Language is clear and professional
• Structure is logical and easy to follow
• Key findings are prominently highlighted
• Recommendations are specific and actionable
• Confidence levels are appropriately communicated

PBSA Industry Relevance:

• Insights are relevant to student accommodation industry
• Market context is appropriately considered
• Seasonal factors are addressed where relevant
• Competitive dynamics are considered
• Regulatory or policy implications noted where applicable

Quality Assessment:

• Excellent: Comprehensive, accurate, well-presented analysis that fully addresses query
• Good: Solid analysis with minor gaps or presentation issues
• Acceptable: Adequate analysis but with some limitations or unclear elements
• Needs Improvement: Significant issues with accuracy, methodology, or presentation
• Unacceptable: Major errors or failure to address query appropriately

Improvement Recommendations:

[Specific suggestions for enhancing the analysis output]"""

def _render(self, **kwargs) -> ChatPromptTemplate:
    """Render the output verification prompt"""
    analysis_output = kwargs.get('analysis_output', '')
    original_query = kwargs.get('original_query', '')
    analysis_methodology = kwargs.get('analysis_methodology', 'Standard PBSA analysis')
    data_sources_used = kwargs.get('data_sources_used', 'PBSA datasets')

    return ChatPromptTemplate.from_messages([
        ("system", self._system_prompt.format(
            analysis_output=analysis_output,
            original_query=original_query,
            analysis_methodology=analysis_methodology,
            data_sources_used=data_sources_used
        ))
    ])

class DataAccuracyPrompt(BasePrompt): """Specialized prompt for validating data accuracy and consistency"""

_required_params = ["data_points", "data_sources"]
_optional_params = ["expected_ranges", "validation_benchmarks"]
_output_schema = None
_node = "data_accuracy"
_tags = ["data_validation", "accuracy", "consistency"]
_version = "1.0"

_system_prompt = """# PBSA DATA ACCURACY VALIDATION

Data Sources: {data_sources}

Expected Ranges: {expected_ranges}

Validation Benchmarks: {validation_benchmarks}

Data Validation Plan:

check_data_completeness Verify all required data points are present and properly populated

validate_numerical_accuracy Check calculations, aggregations, and derived metrics for mathematical correctness

assess_data_consistency Ensure data points are internally consistent and align with related metrics

verify_industry_benchmarks Compare data against known PBSA industry standards and typical ranges

identify_outliers Flag any data points that seem unusually high or low and verify their accuracy

Data Points to Validate:

{data_points}

PBSA Data Validation Standards:

Occupancy Metrics:

• Typical Range: 85-98% for peak academic periods
• Red Flags: >100% (overbooking issues), <70% (underperformance)
• Consistency Check: Let rate vs. actual occupancy alignment

Pricing Metrics:

• Typical Range: £100-400 per week depending on location and amenity level
• Red Flags: Extreme outliers beyond market norms
• Consistency Check: Average rent vs. room type pricing alignment

Revenue Metrics:

• RevPAB Range: Varies by market but should align with occupancy × average rate
• Red Flags: Revenue calculations that don't match occupancy and pricing
• Consistency Check: Total revenue vs. sum of individual property revenues

Temporal Consistency:

• Seasonal Patterns: Higher occupancy in academic months (Sep-May)
• Booking Velocity: Peak booking periods (Jan-May for following academic year)
• Year-over-Year: Gradual changes rather than dramatic shifts unless explained

Validation Outcomes:

• Validated: Data passes all consistency and accuracy checks
• Flagged: Data contains potential issues requiring investigation
• Rejected: Data contains significant errors requiring correction
• Conditional: Data is acceptable with noted limitations or assumptions"""

{question}