Factory Telemetry and Automated OEE Reporting Architecture Specification
Define technical data modeling, metric calculation rules, and visualization specs for automated shopfloor OEE reporting.
Use this specification prompt when architecting unified telemetry and downtime reporting across discrete or continuous manufacturing assets. It bridges shopfloor OT historian tags with executive and shift-level BI reporting layers.
Role: Principal Manufacturing Telemetry & BI Architect with 15+ years designing enterprise industrial reporting systems.
Context
- Manufacturing site and operational footprint: {{plant_location}}
- Industrial automation & historian infrastructure: {{scada_historian_stack}}
- Production lines and machine assets in scope: {{line_equipment_scope}}
- Required report refresh rates and aggregation levels: {{target_reporting_cadence}}
- Standard downtime taxonomy & fault tagging schema: {{downtime_categorization_standard}}
- Target user personas and decision workflows: {{stakeholder_user_groups}}
Task
Generate a comprehensive technical reporting specification for an automated Overall Equipment Effectiveness (OEE) and machine telemetry analytics system, translating raw plant floor sensor data into auditable shift, daily, and executive reports.
Method
- Define ingestion pipelines from {{scada_historian_stack}} covering tag validation, deadband filtering, and edge buffering for {{line_equipment_scope}}.
- Formulate explicit mathematical logic for Availability, Performance, and Quality components using {{downtime_categorization_standard}}.
- Map micro-stoppages, planned maintenance, and unplanned breakdown events into structured reporting dimensional models.
- Design aggregation schedules and data roll-up mechanisms matching {{target_reporting_cadence}} for {{plant_location}}.
- Specify role-tailored dashboard views, alert thresholds, and anomaly indicators for {{stakeholder_user_groups}}.
- Detail data governance, automated sensor drift reconciliation, and missing telemetry imputation protocols.
- Outline export schemas, REST query endpoints, and PDF/tabular push notification parameters.
Constraints
- MUST define exact formulaic boundaries and edge-case behaviors for shift overlaps and unclassified downtime.
- MUST NOT leave raw OPC-UA/MQTT historian tag names unmapped to standardized semantic business dimensions.
- Specifications MUST include explicit latency benchmarks from PLC trigger to dashboard visualization.
- Formulas must account for scheduled unworked periods without distorting net operational availability.
Output format
Provide the specification in 5 structured sections:
- Executive Architecture Summary (max 200 words)
- Telemetry Ingestion & Metric Calculation Engine (exact mathematical definitions & pseudocode)
- Dimensional Data Model & Entity Relationship Schema (markdown data dictionary)
- Stakeholder Reporting UX & Visual Wireframe Specifications (3 distinct persona view definitions)
- Validation, Auditing & Failover Protocol (data quality SLAs & imputation rules)
Self-review
- Confirm all variables from {{plant_location}} to {{stakeholder_user_groups}} are explicitly integrated.
- Verify OEE calculation logic rigorously separates planned exclusions from unplanned availability loss.
- Ensure reporting refresh rates adhere strictly to {{target_reporting_cadence}} requirements.
Explicit role, a named task, and discrete steps the model can follow.
Background, inputs and variables the model needs before it starts.
Hard boundaries — what the model must and must not do.
A named, field-level shape for the response.
Ordered work items that force analysis before an answer.
Length and structure that travel across frontier models.
Signal density — instruction weight without padding.
Documented variables so the scaffold adapts to new inputs.
Quality bar, assumptions and behaviour when inputs are thin.
How much real usage the template has behind it.