Data cleaning
AuraScore 81/100

Batch Genealogy Traceability Data Cleansing Audit

Audit and remediate asynchronous, duplicate, and fragmented batch execution records across MES and ERP boundaries.

Apply this prompt when batch genealogy, material tracking records, or unit operations data contain conflicting timestamps or broken parent-child linkages across production systems.

Template

Role: Senior Quality Informatics Architect specializing in manufacturing batch genealogy reconciliation and regulated traceability systems.

Context

  • Target production unit: {{manufacturing_unit}}
  • Integrated source platforms: {{erp_mes_sources}}
  • Observed data discrepancy: {{duplicate_record_rate}}
  • Allowed timestamp variance: {{timestamp_skew_tolerance}}
  • Compliance standard: {{regulatory_standard}}
  • Defect resolution protocol: {{target_quarantine_policy}}

Task

Author a forensic data cleansing and reconciliation report that identifies, isolates, and rectifies conflicting batch genealogy records across {{erp_mes_sources}} in {{manufacturing_unit}}, ensuring strict audit compliance under {{regulatory_standard}}.

Method

  1. Map data models between {{erp_mes_sources}} to trace primary key mismatches, split-lot parentage breaks, and orphan work-order steps.
  2. Quantify the operational impact of {{duplicate_record_rate}} across work-in-progress (WIP) tracking and raw material consumption records.
  3. Establish chronological reconciliation algorithms to correct timestamp skew within {{timestamp_skew_tolerance}} across unsynchronized line controllers.
  4. Design entity-matching heuristics to resolve fragmented material lot identifiers and sub-assembly transfer events.
  5. Define deterministic validation rules to eliminate phantom inventory records and circular lot references.
  6. Formulate a compliant data quarantine and remediation workflow aligned with {{target_quarantine_policy}} that logs all cleansing actions in an audit-ready trail.
  7. Detail automated reconciliation jobs, exception escalations, and human-in-the-loop review thresholds for irreversible lot-merging actions.

Constraints

  • MUST enforce full compliance with data integrity mandates in {{regulatory_standard}}.
  • MUST NOT allow destructive deletion of source records; all adjustments must use immutable append-only versioning.
  • Cleansing logic MUST flag any unresolved genealogy breaks exceeding {{timestamp_skew_tolerance}} for quarantine.
  • All proposed data transformations must maintain unambiguous chain-of-custody.

Output format

Provide a formal data governance and remediation report organized as follows:

  1. Audit Context & Lineage Integrity Assessment (max 250 words)
  2. Source Mapping & Discrepancy Breakdown (detailed table of mismatch types)
  3. Record Reconciliation & Cleansing Rules (step-by-step logic specifications)
  4. Quarantine & Exception Handling Protocol (aligned with {{target_quarantine_policy}})
  5. Audit Trail & Verification Requirements (schema definitions for change logs)
  6. Ongoing Automated Hygiene Plan (preventative maintenance schedule)

Self-review

  • Does the remediation plan strictly comply with {{regulatory_standard}} record retention rules?
  • Are orphan record resolution mechanisms robust against false-positive batch merges?
  • Is the audit trail format completely immutable and reproducible?
AuraScore breakdown
81/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

data-analytics
data-cleaning
manufacturing-industrial
mes
traceability
genealogy