Iteration 0 - OR_EXPERT
Sequence: 1
Timestamp: 2025-07-25 22:39:32

Prompt:
You are an Operations Research (OR) expert focused ONLY on optimization modeling. Your role is to analyze the business domain and design LINEAR optimization problems without involving database design decisions.

CRITICAL MATHEMATICAL CONSTRAINTS FOR LINEAR/MIXED-INTEGER PROGRAMMING:
- The optimization problem MUST be either Linear Programming (LP) or Mixed-Integer Programming (MIP)
- Objective function MUST be linear: minimize/maximize ∑(coefficient × variable)
- All constraints MUST be linear: ∑(coefficient × variable) ≤/≥/= constant
- Decision variables can be continuous (LP) or mixed continuous/integer (MIP)
- NO variable products, divisions, or other nonlinear relationships
- Design business scenarios that naturally lead to linear mathematical formulations
- Generate between 2 and 20 constraints for optimization feasibility

YOUR SCOPE: Focus exclusively on optimization modeling and understanding current schema-to-optimization mapping. Do NOT propose database changes.
ROW COUNT AWARENESS: Be aware that data engineer will apply 3-row minimum rule - tables unable to generate sufficient meaningful rows will be moved to business_configuration_logic.json.

CRITICAL: Respond with ONLY a valid JSON object. No explanations, no markdown, no extra text.

Database: scientist_1

```sql
CREATE TABLE Scientists (
  SSN NUMBER,
  Name TEXT
);
```

```sql
CREATE TABLE Projects (
  Code TEXT,
  Name TEXT,
  Hours NUMBER
);
```

```sql
CREATE TABLE AssignedTo (
  Scientist NUMBER,
  Project TEXT
);
```



Current Business Configuration Logic: {} (initially empty)

TASK: Design a realistic LINEAR optimization problem and analyze how it maps to the current schema.

JSON STRUCTURE REQUIRED:

{
  "database_id": "scientist_1",
  "iteration": 0,
  "business_context": "Describe the realistic business scenario that leads to linear optimization (avoid scenarios requiring nonlinear relationships)",
  "optimization_problem_description": "Detailed description of what needs to be optimized using linear objective functions and constraints",
  "optimization_formulation": {
    "objective": "minimize/maximize specific_linear_metric with clear definition (sum of weighted variables only)",
    "decision_variables": "What linear variables can be controlled/decided (continuous or integer)",
    "constraints": "What linear limitations must be respected (no variable products or divisions) - design 2 to 20 constraints"
  },
  
  "current_optimization_to_schema_mapping": {
    "objective_coefficients": {
      "coefficient_name[indices]": {
        "currently_mapped_to": "table.column OR business_configuration_logic.key OR missing",
        "mapping_adequacy": "good/missing/redundant/partial/inaccurate",
        "description": "what this coefficient represents in the optimization model"
      }
    },
    "constraint_bounds": {
      "constraint_name[indices]": {
        "currently_mapped_to": "table.column OR business_configuration_logic.key OR missing", 
        "mapping_adequacy": "good/missing/redundant/partial/inaccurate",
        "description": "what this constraint bound represents"
      }
    },
    "decision_variables": {
      "variable_name[indices]": {
        "currently_mapped_to": "table.column OR business_configuration_logic.key OR missing",
        "mapping_adequacy": "good/missing/redundant/partial/inaccurate", 
        "description": "what this decision variable represents",
        "variable_type": "continuous/integer/binary"
      }
    }
  },
  
  "missing_optimization_requirements": [
    "List what data/parameters are needed for complete linear optimization model"
  ],
  
  "iteration_status": {
    "complete": false,
    "confidence": "low/medium/high",
    "next_focus": "What optimization aspects need refinement"
  }
}

Response:
{
  "database_id": "scientist_1",
  "iteration": 0,
  "business_context": "A research institute needs to assign scientists to projects in a way that minimizes the total project hours while ensuring that each scientist is assigned to at least one project and no project exceeds its maximum allowed hours.",
  "optimization_problem_description": "The goal is to minimize the total project hours by optimally assigning scientists to projects. Constraints include ensuring each scientist is assigned to at least one project, no project exceeds its maximum allowed hours, and each project has at least one scientist assigned.",
  "optimization_formulation": {
    "objective": "minimize \u2211(Hours \u00d7 x_{ij}) where x_{ij} is a binary variable indicating if scientist i is assigned to project j",
    "decision_variables": "x_{ij} (binary): 1 if scientist i is assigned to project j, 0 otherwise",
    "constraints": [
      "\u2211(x_{ij}) \u2265 1 for each scientist i (each scientist must be assigned to at least one project)",
      "\u2211(x_{ij}) \u2264 MaxHours_j for each project j (no project exceeds its maximum allowed hours)",
      "\u2211(x_{ij}) \u2265 1 for each project j (each project must have at least one scientist assigned)"
    ]
  },
  "current_optimization_to_schema_mapping": {
    "objective_coefficients": {
      "Hours[j]": {
        "currently_mapped_to": "Projects.Hours",
        "mapping_adequacy": "good",
        "description": "Hours required for project j"
      }
    },
    "constraint_bounds": {
      "MaxHours_j[j]": {
        "currently_mapped_to": "missing",
        "mapping_adequacy": "missing",
        "description": "Maximum allowed hours for project j"
      }
    },
    "decision_variables": {
      "x_{ij}[i,j]": {
        "currently_mapped_to": "AssignedTo.Scientist, AssignedTo.Project",
        "mapping_adequacy": "partial",
        "description": "Assignment of scientist i to project j",
        "variable_type": "binary"
      }
    }
  },
  "missing_optimization_requirements": [
    "Maximum allowed hours for each project (MaxHours_j)",
    "Binary decision variables for assignment (x_{ij})"
  ],
  "iteration_status": {
    "complete": false,
    "confidence": "medium",
    "next_focus": "Define maximum allowed hours for each project and refine the mapping of decision variables"
  }
}
