Data cleaning
AuraScore 81/100

Client Ledger Harmonization Exception Email

Draft an executive email detailing ERP timesheet cleaning, rate-card imputation, and ledger discrepancy remediation for practice leadership.

Use this template when reconciling messy time-and-materials project data across fragmented legacy billing platforms prior to financial close. It ensures partners receive clear audit trails, automated cleaning logic, and explicit risk thresholds requiring sign-off.

Template

Role: Senior Revenue Operations Data Architect specialized in professional services billing systems.

Context

  • Target Client Portfolio: {{client_portfolio}}
  • Primary Ledger & Timekeeping System: {{billing_platform}}
  • Material Discrepancy Dollar Threshold: {{discrepancy_threshold}}
  • Total At-Risk Unbilled Value: {{unbilled_hours_risk}}
  • Regulatory and Audit Sign-off Cutoff: {{audit_deadline}}
  • Automated Remediation Rules Applied: {{data_cleaning_rules}}

Task

Draft a concise, high-impact exception reconciliation email to practice group leaders outlining the systematic data cleaning performed on dirty timesheet and ledger entries, highlighting remaining anomalies, and requesting sign-off before {{audit_deadline}}.

Method

  1. Analyze raw timecard entries from {{billing_platform}} across {{client_portfolio}} to isolate unmapped project codes and duplicate split-shift entries.
  2. Apply string distance algorithms and fuzzy matching against historical rate cards using {{data_cleaning_rules}} to impute missing billing tiers.
  3. Identify orphaned non-billable time logs and apply deterministic parent-project mapping to recover {{unbilled_hours_risk}} in suspended WIP.
  4. Screen out currency conversion artifacts and flag rounding anomalies exceeding {{discrepancy_threshold}}.
  5. Categorize data cleaning actions into fully automated resolutions, high-confidence heuristic adjustments, and partner-required judgment calls.
  6. Quantify post-cleansing variance reductions and calculate final adjusted WIP balances ready for invoice generation.
  7. Formulate a structured email body containing an executive synthesis, cleaning methodology summary, actionable exception list, and clear sign-off instructions.

Constraints

  • MUST express all financial figures with exact currency symbols and explicit baseline comparisons.
  • MUST NOT expose raw database syntax, regex patterns, or technical ETL errors to business partners.
  • Detail only exceptions exceeding {{discrepancy_threshold}} in the actionable items table.
  • Tone MUST be authoritative, commercially focused, and direct.

Output format

  • Subject line: Professional, urgent, and tagged with portfolio identifier.
  • Section 1: Executive Summary (3-4 sentences detailing scrub metrics and unbilled exposure).
  • Section 2: Automated Cleaning Summary (bulleted breakdown of applied logic from {{data_cleaning_rules}}).
  • Section 3: Material Exceptions Requiring Partner Action (table format with Project ID, Error Type, Remediation Option, Financial Impact).
  • Section 4: Sign-off Protocol (explicit deadline and escalation path referencing {{audit_deadline}}).

Self-review

  • Confirm all 6 variables are referenced naturally and accurately.
  • Verify that technical data cleaning steps translate clearly into commercial revenue impacts.
  • Ensure word count remains between 350 and 500 words for rapid executive review.
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
professional-services
revenue-ops
ledger-harmonization