Operator-ready prompt for reuse, tuning, and workspace runs.
This item is set up for developers who want to inspect the original language, fork it into Workspace, and adapt the evidence model without losing the source prompt structure.
Implementation handoffs, eval setup, and prompt tuning where you need the original structure intact.
Inspect first, copy once, then fork into Workspace when you want variants, notes, and model settings attached to the same run.
Swap domain facts, examples, and any hard-coded entities for your own context.
Tighten the evidence or verification requirement if this is headed toward production.
Decide which failure mode you want to evaluate first before you branch the prompt.
This prompt already carries implementation detail, tool context, and a final-output instruction. Keep that structure intact when you tune it, or your comparison runs get noisy fast.
Open this prompt inside Workspace when you want a live iteration loop.
Copy for quick reuse, or run it in Workspace to keep prompt variants, model settings, and prompt-history changes in one place.
Structured source with 60 active lines to adapt.
Already linked to a challenge workflow.
Sign in to keep private prompt variations.
Prompt content
Original prompt text with formatting preserved for inspection and clean copy.
Initialize your OpenAI Agent using `OpenAI Agents SDK`. Define a tool named `policy_retriever` that can query the Supabase vector database for relevant policy documents based on a search query. Also, define a tool named `mem0_saver` to persist critical audit findings or contextual information to Mem0 for long-term memory. Your agent should be configured to use `GPT-4o` as its underlying model.
```python
from openai import OpenAI
import os
# Assume Supabase client and Mem0 client are initialized elsewhere
# from supabase_client import get_policy_documents
# from mem0_client import save_to_mem0
client = OpenAI(api_key=os.environ.get('OPENAI_API_KEY'))
def policy_retriever(query: str):
# This function would interact with your Supabase Vector DB
print(f"Searching Supabase for policies related to: {query}")
# Example: return get_policy_documents(query)
return ["Policy A: Data retention policies.", "Policy B: Consent guidelines."]
def mem0_saver(key: str, value: str):
# This function would save information to Mem0
print(f"Saving to Mem0: {key} = {value}")
# Example: save_to_mem0(key, value)
return {"status": "success"}
# Tool definitions for OpenAI Agents SDK
tools = [
{
"type": "function",
"function": {
"name": "policy_retriever",
"description": "Retrieves relevant policy documents from a vector database based on a search query.",
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string", "description": "The search query for policy documents."}
},
"required": ["query"]
}
}
},
{
"type": "function",
"function": {
"name": "mem0_saver",
"description": "Persists key-value information into long-term memory via Mem0.",
"parameters": {
"type": "object",
"properties": {
"key": {"type": "string", "description": "The key for the information to save."},
"value": {"type": "string", "description": "The value (content) to save."
}
},
"required": ["key", "value"]
}
}
}
]
# Initialize the Assistant
assistant = client.beta.assistants.create(
name="AI Policy Auditor",
instructions="You are an expert AI policy auditor. Your task is to analyze documents for compliance with ethical guidelines and regulations. Use the provided tools to retrieve relevant policies and save your findings.",
model="gpt-4o", # Or a specific model like 'gpt-4o'
tools=tools
)
print(f"Assistant created with ID: {assistant.id}")
```Adaptation plan
Keep the source stable, then branch your edits in a predictable order so the next prompt run is easier to evaluate.
Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.
Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.
Check whether the prompt asks for the right evidence, confidence signal, and escalation path.
Copy once for a pristine source snapshot, then move the prompt into Workspace when you want variants, run history, and side-by-side tuning without losing the original.
Prompt diagnostics
Quick signals for how structured this prompt already is and where adaptation work is likely to happen first.
This prompt already mixes executable detail with instructions, so the safest path is to tune examples and interfaces before you rewrite the overall scaffold.
AI Policy Audit Agent with OpenAI Agents
Develop an autonomous AI agent leveraging the OpenAI Agents SDK to assist in auditing frontier AI models for policy compliance and ethical guidelines. This agent will ingest large volumes of policy documents, ethical frameworks, and internal model documentation, performing sophisticated RAG to identify potential risks, non-compliance, or areas requiring further human review. Persistent memory via Mem0 will allow the agent to maintain context across multiple audit sessions and learn from prior findings, enhancing its capabilities over time. The system will integrate with Supabase for vector storage of documents and OpenRouter for resilient model access and cost monitoring.
Use the challenge page to recover the original task boundaries before you tune the prompt. That keeps your variants grounded in the same evaluation target instead of drifting into a different problem.