Here is the professional-grade, engineered prompt. You can copy and paste this directly into your LLM of choice.

Prompt: Automated Data Quality Governance & Monitoring System

🎭 Role

Act as a Senior Data Engineer and Analytics Architect with expertise in modern data observability, automated testing frameworks (specifically Great Expectations), and dashboard design. Your goal is to design scalable, production-ready systems that ensure high-fidelity data pipelines.

🌐 Context

We are implementing a robust data quality framework for [ORGANIZATION_NAME], which currently processes [DATA_VOLUME_ESTIMATE] across [STORAGE_PLATFORM]. The objective is to transition from reactive data fixes to proactive quality observability. We need to implement a automated monitoring layer that generates a centralized dashboard for stakeholders while triggering real-time alerts when quality thresholds are breached.

🛠️ Task Instruction

Please design a technical specification and implementation roadmap for an automated data quality monitoring system. Address the following components:

1. Validation Logic Design: Define how to implement the following checks using [TOOL_CHOICE, e.g., Great Expectations or Custom Python]:
   • Completeness: Logic for monitoring null percentage thresholds.
   • Uniqueness: Strategy for identifying and flagging duplicate records.
   • Validity: Approach for implementing regex patterns and statistical range checks.
   • Timeliness: Mechanism for monitoring data freshness (SLA breach detection).
   • Consistency: Logic for cross-table referential integrity and schema drift detection.
2. Alerting Infrastructure: Outline an architecture for routing threshold-breach alerts to [COMMUNICATION_CHANNEL, e.g., Slack/PagerDuty/Email].
3. Dashboard Architecture: Suggest a high-level UI/UX wireframe for a dashboard that tracks "Data Quality Scores" over time. Include key metrics that should be prioritized for executive vs. technical stakeholders.
4. Integration Strategy: Briefly explain how this system integrates into a CI/CD data pipeline (e.g., dbt tests or Airflow orchestration).

⚖️ Constraints & Tone

• Tone: Professional, authoritative, and structured.
• Constraints: Do not provide generic boilerplate code; provide specific library recommendations and architectural patterns. Focus on scalability and performance (avoid heavy compute-intensive validation on massive datasets).
• Avoid: Do not include fluff or redundant introductions.

📝 Output Format

Please provide your response in the following format:

• Executive Summary: A high-level overview of the proposed solution.
• Architecture Diagram/Flow: A text-based representation of the data flow.
• Implementation Roadmap: A step-by-step technical guide addressing the 5 validation pillars.
• Monitoring & Alerting Design: Specific thresholds and escalation logic.
• Dashboard Specifications: Key performance indicators (KPIs) to display.

Placeholders to customize before sending:

• [ORGANIZATION_NAME]: (e.g., Acme Corp / Financial Services Data Team)
• [DATA_VOLUME_ESTIMATE]: (e.g., 5TB daily / millions of rows)
• [STORAGE_PLATFORM]: (e.g., Snowflake, BigQuery, AWS S3/Databricks)
• [TOOL_CHOICE]: (e.g., Great Expectations / Soda / Deequ)
• [COMMUNICATION_CHANNEL]: (e.g., Slack/Microsoft Teams/PagerDuty)