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 Seawater RO Membrane Spare-Parts Procurement and Clean Outage Scheduler

Format
Code-aware
Lines
96
Sections
11
Linked challenge
Build a Seawater RO Membrane Spare-Parts Procurement and Clean Outage Scheduler

Prompt source

Original prompt text with formatting preserved for inspection.

96 lines
11 sections
No variables
1 code block
## Build
Correlate seawater reverse osmosis membrane fouling metrics from WaterTAP flowsheets with chemical wash inventory and spare membrane stock. Plan multi-train cleaning outages to prevent potable water supply interruptions.

## User
Desalination Plant Operations Manager

## Workflow
1. Parse WaterTAP reverse osmosis train flowsheet parameters including normalized flux and salt rejection.
2. Calculate membrane degradation trends and evaluate Clean-In-Place chemical consumption requirements.
3. Inspect warehouse inventory for replacement spiral-wound membrane elements and antiscalant stock.
4. Synthesize multi-train outage sequence schedules while maintaining water reservoir reserve commitments.

## Interface
FastAPI backend connected to an operations dashboard displaying RO train health, CIP schedules, and inventory alerts.

## Data
Construct synthetic RO membrane operating datasets mimicking WaterTAP RO flowsheet state variables under Persian Gulf salinity (42,000 ppm TDS).
Starter examples below are synthetic. They are not downloaded records.

## Source
[WaterTAP treatment modeling](https://raw.githubusercontent.com/watertap-org/watertap/main/README.md)
Leverages WaterTAP treatment modeling concepts to track membrane mass transfer coefficients, pressure drops, and salt passage.

## Tools
mastra-ai, fastapi, pydantic.
Mastra AI provides resilient workflow orchestration and event logging across multi-stage chemical and membrane operations.
Local or hosted LLM capable of evaluating industrial process constraints and generating structured scheduling JSON.

## 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
- Detects membrane differential pressure increase exceeding 20% baseline signaling mandatory CIP.
- Verifies on-site citric acid and sodium hydroxide cleaning chemical stock before scheduling train shutdown.
- Ensures total plant potable production never drops below 80% contract commitment during outages.
- Emits formal maintenance work ticket requiring plant engineering sign-off.

## Starter Examples
```json
[
  {
    "input": {
      "plant_id": "FUJAIRAH-RO-T2",
      "train_id": "TRAIN-B",
      "differential_pressure_bar": 3.8,
      "baseline_pressure_bar": 2.9,
      "salt_rejection_percent": 98.2,
      "finished_water_storage_hours": 18,
      "warehouse_stock": {
        "citric_acid_kg": 1500,
        "naoh_kg": 800,
        "spare_swro_elements": 24
      },
      "required_cip_chemicals": {
        "citric_acid_kg": 600,
        "naoh_kg": 300
      }
    },
    "expected_output": {
      "plant_id": "FUJAIRAH-RO-T2",
      "train_id": "TRAIN-B",
      "cip_action_required": true,
      "dp_increase_percent": 31.03,
      "chemical_inventory_sufficient": true,
      "membrane_replacement_needed": false,
      "recommended_outage_start": "Day 2 at 22:00 (Reservoir above 14h safety buffer)",
      "outage_duration_hours": 8,
      "requires_chief_operator_signoff": true
    }
  },
  {
    "input": {
      "plant_id": "AL-ZOUR-SWRO-1",
      "train_id": "TRAIN-D",
      "differential_pressure_bar": 4.5,
      "baseline_pressure_bar": 3,
      "salt_rejection_percent": 94.1,
      "finished_water_storage_hours": 7,
      "warehouse_stock": {
        "citric_acid_kg": 200,
        "naoh_kg": 150,
        "spare_swro_elements": 4
      },
      "required_cip_chemicals": {
        "citric_acid_kg": 600,
        "naoh_kg": 300
      }
    },
    "expected_output": {
      "plant_id": "AL-ZOUR-SWRO-1",
      "train_id": "TRAIN-D",
      "cip_action_required": true,
      "dp_increase_percent": 50,
      "chemical_inventory_sufficient": false,
      "membrane_replacement_needed": true,
      "recommended_outage_start": "BLOCKED: Storage buffer low (7h < 12h threshold) and chemical deficit",
      "outage_duration_hours": 16,
      "requires_chief_operator_signoff": true
    }
  }
]
```

## Safety
High-pressure seawater reverse osmosis trains operate up to 70-80 bar; all pump shutdowns, valving sequences, and chemical washes require human engineering supervision.
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.