Back to Prompt Library
implementation

Implement Client Vetting Agent

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Secure Enterprise Financial Automation

Format
Code-aware
Lines
19
Sections
4
Linked challenge
Secure Enterprise Financial Automation

Prompt source

Original prompt text with formatting preserved for inspection.

19 lines
4 sections
No variables
1 code block
Implement the 'Client Vetting Agent' using the OpenAI Agents SDK. This agent should be capable of: 
1. Receiving client information (refer to `SimulatedClientVetting` input_format). 
2. Calling a mock enterprise API to 'verify identity' and 'check financial history'. 
3. Querying Weaviate for stored compliance rules and past client flags. 
4. Making a decision on client approval and identifying any compliance flags. 

Ensure secure handling of mock data and demonstrate tool use within the OpenAI Agents SDK. Include basic agent initialization like:

```python
from openai import OpenAI

client = OpenAI()
assistant = client.beta.assistants.create(
    name="ClientVettingAgent",
    instructions="You are an expert financial compliance officer. Your role is to vet new clients and ensure they meet all regulatory requirements.",
    model="gpt-4o",
    tools=[
        {"type": "function", "function": {"name": "verify_identity", "description": "Verify client identity...", "parameters": {}}},
        {"type": "function", "function": {"name": "check_financial_history", "description": "Check client's financial background...", "parameters": {}}}
    ]
)
```

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.