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 BODS Terminal Natural Person Verification Profiler
Format
Code-aware
Lines
92
Sections
11
Linked challenge
Build a BODS Terminal Natural Person Verification Profiler
Prompt source
Original prompt text with formatting preserved for inspection.
92 lines
11 sections
No variables
1 code block
## Build
Traverse multi-tier BODS ownership declarations to identify holding structures lacking terminal natural person nodes. Formulate missing verification alerts based on entity termination types.
## User
Corporate Transparency Compliance Analyst
## Workflow
1. Ingest simplified normalized BODS v0.4 ownership statements.
2. Traverse corporate holding paths to locate terminal entity nodes.
3. Evaluate terminal node properties to confirm natural person identifier status.
4. Generate precise evidence requests for paths terminating in unverified corporate vehicles.
## Interface
A tabular tree view visualizing holding chains alongside highlighted missing ultimate beneficial owners.
## Data
Mock BODS v0.4 JSON datasets representing multi-jurisdiction ownership chains with varying equity stakes.
Starter examples below are synthetic. They are not downloaded records.
## Source
[Beneficial Ownership Data Standard](https://standard.openownership.org/en/latest/)
BODS v0.4 data model, schema definitions, and entity interest representations.
## Tools
pydantic-ai, fastapi, networkx.
Validates BODS v0.4 data models and structures verified calculation payloads.
Structured JSON reasoning model via API or local runner.
## 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
- Traverses multi-level corporate entity structures to identify terminal nodes.
- Flags holding chains that end in corporate vehicles without a natural person.
- Produces verification alerts targeted at the terminal entity for RFI follow-up.
## Starter Examples
```json
[
{
"input": {
"subject_entity": "Apex Holdings LLC",
"ownership_statements": [
{
"entity": "Apex Holdings LLC",
"held_by": "MidCo Ltd"
},
{
"entity": "MidCo Ltd",
"held_by": "Unknown Trust"
}
]
},
"expected_output": {
"subject_entity": "Apex Holdings LLC",
"terminal_paths": [
{
"path": [
"Unknown Trust",
"MidCo Ltd",
"Apex Holdings LLC"
],
"terminal_node": "Unknown Trust",
"is_natural_person": false
}
],
"rfi_required_for": [
"Unknown Trust"
]
}
},
{
"input": {
"subject_entity": "Clearwater Corp",
"ownership_statements": [
{
"entity": "Clearwater Corp",
"held_by": "Jane Doe"
}
]
},
"expected_output": {
"subject_entity": "Clearwater Corp",
"terminal_paths": [
{
"path": [
"Jane Doe",
"Clearwater Corp"
],
"terminal_node": "Jane Doe",
"is_natural_person": true
}
],
"rfi_required_for": []
}
}
]
```
## Safety
Maintains non-punitive due diligence posture; does not execute direct corporate freeze requests.
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.