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 Cross-Border Prime Mover Public Parking and Dwell Monitor
Format
Code-aware
Lines
82
Sections
11
Linked challenge
Build a Cross-Border Prime Mover Public Parking and Dwell Monitor
Prompt source
Original prompt text with formatting preserved for inspection.
82 lines
11 sections
No variables
1 code block
## Build
Correlate Singapore public heavy vehicle park capacity data with foreign-registered hauler GPS dwell times. Allocate temporary public rest slots to prevent unauthorized overnight curbside parking.
## User
Industrial Estate Yard Master
## Workflow
1. Ingest incoming foreign-registered hauler plate records and real-time GPS dwell duration.
2. Query Singapore public heavy vehicle parking availability records from data.gov.sg.
3. Match waiting prime movers to nearest available legal parking staging bays to enforce rest regulations.
4. Synthesize temporary parking authorization passes with mapped routing to eliminate overnight curbside congestion.
## Interface
A real-time map interface displaying industrial parking zone occupancy, foreign hauler dwell times, and temporary rest authorization passes.
## Data
Download heavy vehicle parking datasets from data.gov.sg and simulate cross-border prime mover GPS coordinates and dwell durations.
Starter examples below are synthetic. They are not downloaded records.
## Source
[Singapore open data API](https://guide.data.gov.sg/developer-guide/api-overview)
Query public heavy vehicle parking availability datasets from data.gov.sg to identify open rest slots.
## Tools
crewai, geopandas, pydantic.
CrewAI provides role-based agent collaboration between yard capacity monitors and compliance planners.
Hosted or local model with spatial reasoning and regulatory compliance verification skills.
## 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
- Matches waiting haulers to public parking spaces within a 5km radius of current location.
- Evaluates cumulative dwell time against maximum threshold to trigger compliance alerts.
- Issues digital temporary rest authorization passes with authorized duration limits.
- Prevents routing trucks to lots with zero recorded available heavy bays.
## Starter Examples
```json
[
{
"input": {
"truck_id": "MY-TRK-881",
"vehicle_registration": "JMD1234",
"current_location": "Jalan Boon Lay",
"dwell_duration_minutes": 140,
"available_parks": [
{
"park_id": "HVP-01",
"name": "Boon Lay Way Heavy Park",
"distance_km": 2.1,
"free_bays": 6
}
]
},
"expected_output": {
"status": "staging_allocated",
"allocated_park": "Boon Lay Way Heavy Park",
"park_id": "HVP-01",
"authorized_rest_hours": 8,
"turn_by_turn": "Head north on Jalan Boon Lay, turn right into Boon Lay Way staging area."
}
},
{
"input": {
"truck_id": "MY-TRK-882",
"vehicle_registration": "JQD9921",
"current_location": "Tuas South Ave 3",
"dwell_duration_minutes": 200,
"available_parks": [
{
"park_id": "HVP-03",
"name": "Tuas South Heavy Park",
"distance_km": 1.5,
"free_bays": 0
}
]
},
"expected_output": {
"status": "compliance_alert",
"allocated_park": null,
"park_id": null,
"authorized_rest_hours": 0,
"turn_by_turn": "Nearest park full. Direct hauler to designated checkpoint overflow zone."
}
}
]
```
## Safety
Allocates parking guidance; does not issue municipal parking fines or override Singapore road safety regulations. Note: examples are simplified synthetic app records, not complete official schema files.
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.