agentic-eval

class EvaluatorOptimizer:
    def __init__(self, score_threshold: float = 0.8):
        self.score_threshold = score_threshold
    
    def generate(self, task: str) -> str:
        return llm(f"Complete: {task}")
    
    def evaluate(self, output: str, task: str) -> dict:
        return json.loads(llm(f"""
        Evaluate output for task: {task}
        Output: {output}
        Return JSON: {{"overall_score": 0-1, "dimensions": {{"accuracy": ..., "clarity": ...}}}}
        """))
    
    def optimize(self, output: str, feedback: dict) -> str:
        return llm(f"Improve based on feedback: {feedback}\nOutput: {output}")
    
    def run(self, task: str, max_iterations: int = 3) -> str:
        output = self.generate(task)
        for _ in range(max_iterations):
            evaluation = self.evaluate(output, task)
            if evaluation["overall_score"] >= self.score_threshold:
                break
            output = self.optimize(output, evaluation)
        return output

class CodeReflector:
    def reflect_and_fix(self, spec: str, max_iterations: int = 3) -> str:
        code = llm(f"Write Python code for: {spec}")
        tests = llm(f"Generate pytest tests for: {spec}\nCode: {code}")
        
        for _ in range(max_iterations):
            result = run_tests(code, tests)
            if result["success"]:
                return code
            code = llm(f"Fix error: {result['error']}\nCode: {code}")
        return code

def evaluate_outcome(task: str, output: str, expected: str) -> str:
    return llm(f"Does output achieve expected outcome? Task: {task}, Expected: {expected}, Output: {output}")

def llm_judge(output_a: str, output_b: str, criteria: str) -> str:
    return llm(f"Compare outputs A and B for {criteria}. Which is better and why?")

RUBRIC = {
    "accuracy": {"weight": 0.4},
    "clarity": {"weight": 0.3},
    "completeness": {"weight": 0.3}
}
 
def evaluate_with_rubric(output: str, rubric: dict) -> float:
    scores = json.loads(llm(f"Rate 1-5 for each dimension: {list(rubric.keys())}\nOutput: {output}"))
    return sum(scores[d] * rubric[d]["weight"] for d in rubric) / 5

## Evaluation Implementation Checklist
 
### Setup
- [ ] Define evaluation criteria/rubric
- [ ] Set score threshold for "good enough"
- [ ] Configure max iterations (default: 3)
 
### Implementation
- [ ] Implement generate() function
- [ ] Implement evaluate() function with structured output
- [ ] Implement optimize() function
- [ ] Wire up the refinement loop
 
### Safety
- [ ] Add convergence detection
- [ ] Log all iterations for debugging
- [ ] Handle evaluation parse failures gracefully