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 BODS Nominee Arrangement and Undisclosed Principal Profiler

Format
Code-aware
Lines
65
Sections
11
Linked challenge
Build a BODS Nominee Arrangement and Undisclosed Principal Profiler

Prompt source

Original prompt text with formatting preserved for inspection.

65 lines
11 sections
No variables
1 code block
## Build
Apply BODS v0.4 nominee guidance to registered officer declarations. Detect proxy arrangements and undisclosed principals, packaging flagged entities into a prioritized due diligence review queue.

## User
Enhanced Due Diligence Investigator

## Workflow
1. Ingest simplified officer registry records and shareholder declaration forms.
2. Apply BODS v0.4 nominee guidance to detect indicators of professional nominee shareholding or directorship.
3. Score discrepancy metrics prioritizing undisclosed principals over registered nominal controllers.
4. Dispatch flagged records to an analyst triage queue with specific undisclosed principal relationship summaries.

## Interface
A review dashboard sorting entities by nominee risk indicators with drill-down inspector tabs.

## Data
Synthesize officer and shareholder filings containing recurring registered agent addresses and proxy clauses.
Starter examples below are synthetic. They are not downloaded records.

## Source
[Beneficial ownership modelling](https://standard.openownership.org/en/latest/standard/modelling/index.html)
BODS v0.4 modelling requirements for representing nominee arrangements and real world identifiers.

## Tools
langgraph, pydantic, fastapi.
Coordinates stateful routing between initial rules-based screening and analyst queue dispatch.
Standard chat or instruction model capable of structured categorization.

## 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 nominee arrangements based on explicit BODS v0.4 indicator criteria.
- Correctly isolates undisclosed principals behind registered nominee structures.
- Generates a prioritized dispatch queue payload for analyst assignment highlighting undisclosed relationship risk.

## Starter Examples
```json
[
  {
    "input": {
      "entity_name": "Panama Horizon SA",
      "officer_name": "Corporate Nominees Ltd",
      "is_nominee": true,
      "nominee_nominator": "Undisclosed Principal"
    },
    "expected_output": {
      "entity_name": "Panama Horizon SA",
      "triage_priority": "HIGH",
      "nominee_flag": true,
      "discrepancy_note": "Nominee officer declared with undisclosed nominator entity.",
      "undisclosed_principal_detected": true
    }
  },
  {
    "input": {
      "entity_name": "Direct Ops Inc",
      "officer_name": "Alice Smith",
      "is_nominee": false,
      "nominee_nominator": null
    },
    "expected_output": {
      "entity_name": "Direct Ops Inc",
      "triage_priority": "LOW",
      "nominee_flag": false,
      "discrepancy_note": "Direct individual officer recorded with no nominee indicators.",
      "undisclosed_principal_detected": false
    }
  }
]
```

## Safety
Outputs investigative queues for human verification without autonomous legal escalation.
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.