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 Coastal Windstorm Parametric Uncertainty Analyzer

Format
Code-aware
Lines
63
Sections
11
Linked challenge
Build a Coastal Windstorm Parametric Uncertainty Analyzer

Prompt source

Original prompt text with formatting preserved for inspection.

63 lines
11 sections
No variables
1 code block
## Build
Evaluate parametric wind speed trigger ambiguity for coastal marine ports using ERA5 atmospheric reanalysis grids. Quantify trigger misclassification probability against synthetic station observations.

## User
Marine Terminal Risk Consultant

## Workflow
1. Define port asset coordinates and wind threshold triggers in meters per second.
2. Retrieve ERA5 10-meter wind components using Copernicus CDS API scripts.
3. Compute maximum sustained wind speeds and calculate spatial interpolation errors.
4. Quantify trigger uncertainty distributions and publish terminal risk memos.

## Interface
Interactive Python CLI and terminal plot view summarizing wind uncertainty distributions.

## Data
Execute CDS API calls for `reanalysis-era5-single-levels` wind variables or use synthetic NetCDF grid samples.
Starter examples below are synthetic. They are not downloaded records.

## Source
[Copernicus Climate Data Store client](https://raw.githubusercontent.com/ecmwf/cdsapi/master/README.rst)
Sets up `cdsapi.Client()` configuration and calls `cds.retrieve` for atmospheric variables with spatial bounding.

## Tools
ray-serve, cdsapi, numpy, scipy.
Ray Serve enables distributed parallel evaluation of parametric trigger simulations across thousands of asset coordinates.
Distributed compute cluster or multi-core local host for numeric simulations.

## 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
- Computes horizontal wind vector magnitude from u and v components accurately.
- Applies parametric trigger criteria with explicit confidence intervals.
- Logs trigger sensitivity variances across neighboring grid points.

## Starter Examples
```json
[
  {
    "input": {
      "port_code": "PORT-EAST-01",
      "u10_m_s": 24,
      "v10_m_s": 18,
      "trigger_threshold_m_s": 28
    },
    "expected_output": {
      "port_code": "PORT-EAST-01",
      "wind_speed_m_s": 30,
      "trigger_exceeded": true,
      "trigger_confidence": 0.94
    }
  },
  {
    "input": {
      "port_code": "PORT-EAST-02",
      "u10_m_s": 15,
      "v10_m_s": 12,
      "trigger_threshold_m_s": 28
    },
    "expected_output": {
      "port_code": "PORT-EAST-02",
      "wind_speed_m_s": 19.21,
      "trigger_exceeded": false,
      "trigger_confidence": 0.99
    }
  }
]
```

## Safety
Produces parametric simulation sensitivity metrics without issuing contractual settlement determinations.
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.