Data cleaning
AuraScore 77/100

Practice Pipeline Sanitization and Account Reconciliation Email

Author a monthly data hygiene email to consulting practice leaders covering CRM deduplication, stale opportunity repair, and account realignment.

Use this template when recurring business development data in professional services CRMs becomes cluttered with duplicates, orphaned accounts, and invalid stages. It delivers clear data remediation results and actions to practice leaders.

Template

Role: Director of Commercial Analytics & Enterprise CRM Operations.

Context

  • Target Practice Group: {{practice_group}}
  • Underlying CRM Infrastructure: {{crm_system}}
  • Stale Activity Definition: {{stale_deal_cutoff_days}}
  • Impacted Pipeline Volume: {{orphaned_revenue_impact}}
  • Domain Normalization Strategy: {{domain_mapping_logic}}
  • Lead Practice Operations Lead: {{escalation_owner}}

Task

Draft an operational data cleansing update and action email to consulting practice leaders within {{practice_group}} detailing the results of automated pipeline deduplication, lead domain normalization, and stage reclassification in {{crm_system}}.

Method

  1. Ingest all open and past-due commercial opportunities for {{practice_group}} from {{crm_system}}.
  2. Execute corporate domain normalization using {{domain_mapping_logic}} to combine fragmented account variations into single global parent records.
  3. Detect duplicate opportunity records created by cross-border engagement teams and merge them into primary pursuit threads.
  4. Identify deals exceeding {{stale_deal_cutoff_days}} with no buyer interaction and automatically reclassify them to dormant holding stages.
  5. Isolate orphaned opportunities lacking assigned engagement partner owners representing {{orphaned_revenue_impact}} in unmanaged pipeline.
  6. Compute data completeness scores across required fields including close dates, target margins, and primary service line classifications.
  7. Compile a structured email that conveys data hygiene wins, highlights automated fixes, and provides a clear 5-day action list for {{escalation_owner}}.

Constraints

  • MUST clearly separate automated programmatic changes from items requiring manual partner intervention.
  • MUST NOT hard-delete opportunities without an unrecoverable duplicate flag.
  • Include exact percentages for pipeline data completeness before and after cleaning.
  • Maintain an assertive, operational tone focused on forecast accuracy and pipeline hygiene.

Output format

  • Subject: Data Sanitization & Pipeline Health Notice | {{practice_group}} - [Date]
  • Section 1: Cleansing Operations Overview (Summary of records processed in {{crm_system}} and net pipeline variance).
  • Section 2: Automated Actions Executed (Summary of merged accounts, pruned duplicates, and {{domain_mapping_logic}} results).
  • Section 3: Orphaned & Stale Opportunity Intervention (Specific breakdown of {{orphaned_revenue_impact}} needing partner re-assignment).
  • Section 4: Required Partner Actions (Bullet points with clear 5-day deadlines coordinated with {{escalation_owner}}).

Self-review

  • Verify that all 6 template variables are referenced accurately.
  • Check that the transition from raw data cleaning logic to commercial pipeline management is cohesive.
  • Confirm formatting is tailored for quick scanning on mobile devices by practice partners.
AuraScore breakdown
77/100Provisional
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 engineering8/12 · Adequate

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
pipeline-hygiene
crm-operations
sales-analytics