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 an IFC Accessibility Ramp and Door Auditor

Format
Code-aware
Lines
94
Sections
11
Linked challenge
Build an IFC Accessibility Ramp and Door Auditor

Prompt source

Original prompt text with formatting preserved for inspection.

94 lines
11 sections
No variables
1 code block
## Build
Inspect door clear widths and ramp inclinations in architectural IFC models to assess compliance with accessibility guidelines. Generate remedial design tasks for substandard circulation routes.

## User
Universal Design Accessibility Auditor

## Workflow
1. Query IfcDoor and IfcRamp elements with dimensions from architectural model files.
2. Compare clear door opening widths against the standard 850mm barrier-free threshold.
3. Calculate ramp slope gradients and identify segments exceeding maximum 1:12 inclination.
4. Produce prioritized non-conformance action items for architectural revision.

## Interface
Accessibility scorecard dashboard displaying non-compliant circulation elements with direct 3D tags.

## Data
Sample IFC building models containing internal doors and circulation ramps from open IFC repositories.
Starter examples below are synthetic. They are not downloaded records.

## Source
[IfcOpenShell](https://raw.githubusercontent.com/IfcOpenShell/IfcOpenShell/v0.8.0/README.md)
Leverages IfcOpenShell Python schema parsing APIs and ifcbimtester test definitions for property validation.

## Tools
pydantic-ai, fastapi, rich.
Pydantic AI guarantees structured validation of geometric element properties and accessibility rule outputs.
Fast inference model specialized in numerical condition checking and technical compliance documentation.

## 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
- Processes IfcDoor and IfcRamp entity parameters extracted via IfcOpenShell conventions.
- Flags doors with clear width below 0.85 meters.
- Flags ramps with slope gradient steeper than 8.33 percent (1:12 slope).

## Starter Examples
```json
[
  {
    "input": {
      "door_elements": [
        {
          "id": "DOOR-01",
          "name": "Main Entrance",
          "overall_width_m": 0.95,
          "clear_width_m": 0.88
        }
      ],
      "ramp_elements": [
        {
          "id": "RAMP-01",
          "length_m": 6,
          "rise_m": 0.45
        }
      ]
    },
    "expected_output": {
      "compliant_elements": 2,
      "violations": 0,
      "audit_pass": true,
      "remediation_tasks": []
    }
  },
  {
    "input": {
      "door_elements": [
        {
          "id": "DOOR-02",
          "name": "Restroom Door",
          "overall_width_m": 0.8,
          "clear_width_m": 0.74
        }
      ],
      "ramp_elements": [
        {
          "id": "RAMP-02",
          "length_m": 4,
          "rise_m": 0.5
        }
      ]
    },
    "expected_output": {
      "compliant_elements": 0,
      "violations": 2,
      "audit_pass": false,
      "remediation_tasks": [
        {
          "element_id": "DOOR-02",
          "issue": "Clear width 0.74m is less than mandatory 0.85m"
        },
        {
          "element_id": "RAMP-02",
          "issue": "Slope 12.5% exceeds maximum permitted 8.33% (1:12)"
        }
      ]
    }
  }
]
```

## Safety
Accessibility audit results assist architects; official building code approval must be granted by code compliance officials.
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.