TalentPerformer
Guardrails
AI Agent StoreGet Started
← Back to Agent Details

Operational Implementation

The Operational Implementation agent supports the practical execution of aging-focused insurance products. It focuses on creating structured workflows for underwriting, policy administration, and distribution channels. It ensures that product blueprints are translated into actionable operational processes, considering efficiency, regulatory compliance, and scalability.

LIVE

Instructions

You are an Operational Implementation expert for aging insurance products. 
Your task is to plan workflows for each product based on the blueprint and operational guidelines.

Tools to use:
- OpsImplementationPlanner: Generate structured workflows for underwriting, policy administration, and distribution.
- FileTools: Access or read supporting CSV/Excel data files.
- CalculatorTools: Perform any operational calculations if required.
- ReasoningTools: Provide insights, check consistency, and ensure best practices.

Documents (CSV):
- CSV: Product blueprints (Documents/agent2.csv)
- CSV: Operational guidelines (Documents/agent2.csv)

Knowledge Base:
- Markdown knowledge base (kb5) containing product features, pensions, annuities, LTC, innovation trends, and design challenges.

Respond with detailed operational workflows, highlighting the sequence of activities and any dependencies.
Provide output in a JSON format suitable for further processing.

Knowledge Base (.md)

Business reference guide

Drag & Drop or Click

.md, .txt, .pdf

Data Files

Upload data for analysis (CSV, JSON, Excel, PDF)

Drag & Drop or Click

Multiple files: .json, .csv, .xlsx, .xls, .pdf, .docx, .pptx, .txt

Tools 4

OpsImplementationPlanner

Model for storing functions that can be called by an agent.

@tool(name="OpsImplementationPlanner", description="Generate operational workflows for underwriting, policy administration, and distribution channels.", show_result=True)
def OpsImplementationPlanner(
    product_blueprint_csv: str = None,
    operational_guidelines_csv: str = None,
) -> str:
    """
    Generate operational workflows for underwriting, policy administration, and distribution channels.

    Args:
        product_blueprint_csv: Path to CSV with product blueprint specifications.
        operational_guidelines_csv: CSV with operational guidelines and best practices.

    Returns:
        str: JSON string with suggested workflows for each product.
    """
    product_blueprint_csv = product_blueprint_csv or _path("agent2.csv")
    operational_guidelines_csv = operational_guidelines_csv or _path("agent2.csv")
    try:
        blueprints = pd.read_csv(product_blueprint_csv)
        guidelines = pd.read_csv(operational_guidelines_csv)
        workflows = []
        for _, product in blueprints.iterrows():
            uw = "Standard financial/medical underwriting"
            pa = "Standard long-term policy admin"
            dist = "Bancassurance / brokers / corporate partnerships"
            if "Underwriting" in guidelines.columns and len(guidelines) > 0:
                uw = str(guidelines["Underwriting"].iloc[0])
            if "PolicyAdmin" in guidelines.columns and len(guidelines) > 0:
                pa = str(guidelines["PolicyAdmin"].iloc[0])
            if "Distribution" in guidelines.columns and len(guidelines) > 0:
                dist = str(guidelines["Distribution"].iloc[0])
            workflow = {
                "ProductID": product["ProductID"] if "ProductID" in product.index else "",
                "ProductName": product["ProductName"] if "ProductName" in product.index else "",
                "UnderwritingWorkflow": uw,
                "PolicyAdministrationWorkflow": pa,
                "DistributionWorkflow": dist,
            }
            workflows.append(workflow)
        return json.dumps(workflows, indent=2)
    except Exception as e:
        return json.dumps({"error": str(e)})

file_tools

FileTools from agno framework

calculator

CalculatorTools from agno framework

reasoning_tools

ReasoningTools from agno framework

Test Agent

Configure model settings at the top, then test the agent below

Enter your question or instruction for the agent