Skip to main content
Back to Prompt Library
implementation

Build the application

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Build a Sparkplug B Sensor Drift Calibration Rebalancer

Format
Code-aware
Lines
67
Sections
11
Linked challenge
Build a Sparkplug B Sensor Drift Calibration Rebalancer

Prompt source

Original prompt text with formatting preserved for inspection.

67 lines
11 sections
No variables
1 code block
## Build
Evaluate normalized Sparkplug B dataset metrics against sensor calibration thresholds to detect measurement drift. Synthesize a recalibration and replacement schedule for instrumentation technicians.

## User
Instrumentation Lead

## Workflow
1. Ingest normalized Sparkplug B device metric records containing calibration dates and drift standard deviations.
2. Compare sensor variance against published allowable tolerance thresholds.
3. Generate a prioritized recalibration schedule grouped by line and technician specialization.
4. Export a simulated maintenance dispatch record for supervisor sign-off.

## Interface
Terminal dashboard showing sensor drift variance and calendar calibration rosters.

## Data
Generate local synthetic JSON mock streams containing normalized Sparkplug B metric records with sensor serials and baseline offsets.
Starter examples below are synthetic. They are not downloaded records.

## Source
[Eclipse Sparkplug](https://raw.githubusercontent.com/eclipse-sparkplug/sparkplug/master/README.md)
Utilizes Sparkplug B metric property metadata, dataset types, and device lifecycle states outlined in Source 2.

## Tools
pydantic-ai, fastapi.
Pydantic AI provides strict schema enforcement on nested metric records and validation of calibration schedules.
Local small LLM (e.g., Llama 3 8B) or hosted Claude via API for schedule synthesis.

## Deliverables
Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

## Acceptance
- Correctly flags sensors exceeding tolerance thresholds.
- Calculates replacement due dates based on historical calibration intervals.
- Emits valid JSON schedule artifacts matching the schema.

## Starter Examples
```json
[
  {
    "input": {
      "device_id": "EDGE-NODE-01/DEV-TEMP-99",
      "metric_name": "FurnaceTemp",
      "last_calibrated_days": 190,
      "drift_deviation_pct": 4.2,
      "max_allowed_drift_pct": 2.5
    },
    "expected_output": {
      "device_id": "EDGE-NODE-01/DEV-TEMP-99",
      "action_required": "RECALIBRATE",
      "priority": "HIGH",
      "estimated_labor_hours": 1.5,
      "recommended_window": "NEXT_DOWNTIME_SHIFT"
    }
  },
  {
    "input": {
      "device_id": "EDGE-NODE-02/DEV-PRESS-04",
      "metric_name": "HydraulicPressure",
      "last_calibrated_days": 45,
      "drift_deviation_pct": 0.8,
      "max_allowed_drift_pct": 3
    },
    "expected_output": {
      "device_id": "EDGE-NODE-02/DEV-PRESS-04",
      "action_required": "MONITOR",
      "priority": "LOW",
      "estimated_labor_hours": 0,
      "recommended_window": "ROUTINE_CYCLE"
    }
  }
]
```

## Safety
Read-only advisory tool; produces draft maintenance calendars without commanding field instrumentation.
Use mock external writes. Require human review before any real deployment.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.