graph TB
    subgraph Input_Layer [Input & Configuration]
        Config[config.yaml] --> Loader[ConfigLoader]
        Scenarios[(Scenarios Database)] --> Loader
        Oversight[Oversight Levels: low/mid/high] --> Loader
    end

    subgraph Execution_Layer [Experiment Orchestration]
        Loader --> Runner[ExperimentRunner]
        Runner --> Agent[Agent Logic]
        
        subgraph Sandbox [Environment Sandbox]
            Agent <--> VFS[Virtual File System]
            VFS <--> Data[Scenario Data Files]
        end

        Agent <--> LLM[LLM Provider API]
    end

    subgraph Persistence_Layer [Data Persistence]
        Agent --> Logs[Interaction Logs .json]
    end

    subgraph Evaluation_Layer [Multi-Stage Judging]
        Logs --> Judge[Judge Engine]
        
        subgraph Judge_Types [Judging Metrics]
            Judge --> Regex[Regex Checks]
            Judge --> Blackbox[Blackbox LLM Judge: Output Accuracy]
            Judge --> Glassbox[Glassbox LLM Judge: Reasoning Intent]
        end
        
        Regex & Blackbox & Glassbox --> Results[Consolidated Results .csv]
    end

    subgraph Analysis_Layer [Statistical & Visual Analysis]
        Results --> Stats[Statistical Analysis Engine]
        Stats --> Metrics[p-values, Odds Ratios, effect sizes]
        Results --> Viz[Visualization Module]
        Viz --> Charts[Charts & Heatmaps]
    end

    %% Styling
    classDef primary fill:#2563eb,color:#fff,stroke:#1e40af
    classDef secondary fill:#f8fafc,stroke:#64748b,color:#0f172a
    classDef storage fill:#fef3c7,stroke:#d97706,color:#92400e
    
    class Runner,Agent,Judge,Stats primary
    class Config,Scenarios,Oversight secondary
    class Logs,Results,Data storage