TalentPerformer

Continuous Improvement Agent

No description available

LIVE

Instructions

You are a Continuous Improvement specialist focusing on:

1. **Model Enhancements**:
   - Move from deterministic to stochastic ORSA projections
   - Implement ESG/climate risk scenarios
   - Enhance correlation modeling and tail risk assessment

2. **Automation & Efficiency**:
   - Automate ORSA reporting and scenario runs
   - Reduce manual interventions in the closing cycle
   - Implement real-time monitoring and alerting

3. **Feedback Loop**:
   - Post-mortem analysis: compare actual vs. projected solvency movements
   - Improve projection models and assumptions continuously
   - Learn from experience and industry best practices

Use continuous improvement methodologies, technology innovation, and learning frameworks to enhance ORSA processes and outcomes over time.

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 5

stress_test_scenarios

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

@tool(
    name="stress_test_scenarios",
    description="Perform stress testing under various risk scenarios",
    show_result=True,
)
def stress_test_scenarios(
    base_solvency_ratio: float,
    base_scr: float,
    base_own_funds: float,
    stress_scenarios: List[str],
) -> Dict[str, Any]:
    """
    Perform stress testing under various risk scenarios.

    Args:
        base_solvency_ratio: Base solvency ratio
        base_scr: Base SCR amount
        base_own_funds: Base own funds
        stress_scenarios: List of stress scenarios to test

    Returns:
        Dictionary containing stress test results
    """
    scenario_definitions = {
        "interest_rate_shock": {"description": "Parallel shift in interest rates", "scr_impact": 0.05, "own_funds_impact": -0.08},
        "equity_market_crash": {"description": "40% decline in equity markets", "scr_impact": 0.08, "own_funds_impact": -0.12},
        "mortality_stress": {"description": "Pandemic-like mortality increase", "scr_impact": 0.10, "own_funds_impact": -0.15},
        "lapse_shock": {"description": "Mass lapse event", "scr_impact": 0.04, "own_funds_impact": -0.06},
        "credit_default": {"description": "Sovereign default scenario", "scr_impact": 0.06, "own_funds_impact": -0.09},
        "operational_event": {"description": "Major operational failure", "scr_impact": 0.02, "own_funds_impact": -0.20},
    }
    stress_results = {}
    for scenario in stress_scenarios:
        if scenario in scenario_definitions:
            d = scenario_definitions[scenario]
            stressed_scr = base_scr * (1 + d["scr_impact"])
            stressed_own_funds = base_own_funds * (1 + d["own_funds_impact"])
            stressed_solvency_ratio = (stressed_own_funds / stressed_scr) * 100
            stress_results[scenario] = {
                "description": d["description"],
                "base_solvency_ratio": round(base_solvency_ratio, 2),
                "stressed_solvency_ratio": round(stressed_solvency_ratio, 2),
                "impact_on_solvency_ratio": round(stressed_solvency_ratio - base_solvency_ratio, 2),
                "stressed_scr": round(stressed_scr, 0),
                "stressed_own_funds": round(stressed_own_funds, 0),
                "adequacy_level": "Excellent" if stressed_solvency_ratio >= 150 else "Good" if stressed_solvency_ratio >= 130 else "Adequate" if stressed_solvency_ratio >= 100 else "Inadequate",
            }
    return {"base_metrics": {"solvency_ratio": base_solvency_ratio, "scr": base_scr, "own_funds": base_own_funds}, "stress_results": stress_results}

project_solvency_evolution

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

@tool(
    name="project_solvency_evolution",
    description="Project solvency ratio evolution over time under different scenarios",
    show_result=True,
)
def project_solvency_evolution(
    current_solvency_ratio: float,
    current_scr: float,
    current_own_funds: float,
    projection_years: int,
    scenario_type: str,
    assumptions: Dict[str, Any],
) -> Dict[str, Any]:
    """
    Project solvency ratio evolution under different scenarios.

    Args:
        current_solvency_ratio: Current solvency ratio
        current_scr: Current SCR amount
        current_own_funds: Current own funds
        projection_years: Number of years to project
        scenario_type: Type of scenario(base/optimistic/pessimistic)
        assumptions: Dictionary of scenario assumptions

    Returns:
        Dictionary containing projected solvency metrics
    """
    scenario_multipliers = {
        "base": {"scr_growth": 1.02, "own_funds_growth": 1.05, "profit_margin": 0.08},
        "optimistic": {"scr_growth": 1.01, "own_funds_growth": 1.08, "profit_margin": 0.12},
        "pessimistic": {"scr_growth": 1.04, "own_funds_growth": 1.02, "profit_margin": 0.04},
    }
    multipliers = scenario_multipliers.get(scenario_type, scenario_multipliers["base"])
    current_scr_proj = current_scr
    current_own_funds_proj = current_own_funds
    projections = {}
    for year in range(1, projection_years + 1):
        current_scr_proj *= multipliers["scr_growth"]
        profit = current_own_funds_proj * multipliers["profit_margin"]
        current_own_funds_proj += profit
        solvency_ratio = (current_own_funds_proj / current_scr_proj) * 100
        projections[f"year_{year}"] = {
            "solvency_ratio": round(solvency_ratio, 2),
            "scr_amount": round(current_scr_proj, 0),
            "own_funds": round(current_own_funds_proj, 0),
            "profit": round(profit, 0),
            "capital_buffer": round(current_own_funds_proj - current_scr_proj, 0),
        }
    return {
        "scenario_type": scenario_type,
        "projection_years": projection_years,
        "assumptions": assumptions,
        "projections": projections,
    }

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