heading_title_agent_evaluations = Agent Evaluations Monitoring
button_refresh = Refresh
button_back_dashboard = Back to Dashboard
button_close = Close

text_total_evaluations = Total Evaluations
text_average_score = Average Score
text_consensus_sessions = Consensus Sessions
text_consensus_rate = Consensus Rate

text_recent_evaluations = Recent Evaluations
text_score_distribution = Score Distribution

text_evaluator = Evaluator
text_producer = Producer
text_output_type = Output Type
text_overall_score = Overall Score
text_accuracy = Accuracy
text_completeness = Completeness
text_efficiency = Efficiency
text_clarity = Clarity
text_date = Date
text_actions = Actions

text_avg_scores_by_dimension = Average Scores by Dimension
text_dimension = Dimension
text_visual = Visual

text_session_id = Session ID
text_output_id = Output ID
text_participants = Participants
text_status = Status
text_final_score = Final Score
text_created = Created
text_resolved = Resolved

text_evaluation_details = Evaluation Details
text_details = Details
text_number_of_evaluations = Number of Evaluations
text_reached = Reached
text_failed = Failed
text_pending = Pending
text_na = N/A
text_none = None

text_evaluation_id = Evaluation ID
text_scores = Scores
text_overall = Overall
text_feedback = Feedback
text_strengths = Strengths
text_improvements = Improvements
text_evaluated = Evaluated

help_title = Help - Understanding Agent Evaluations
help_description = This page displays quality evaluations performed by critic agents on responses produced by actor agents.
help_scores = <strong>Scores (0-5):</strong> Accuracy = data correctness, Completeness = response exhaustiveness, Efficiency = resource optimization, Clarity = readability and structure.
help_consensus = <strong>Consensus Sessions:</strong> When multiple critics evaluate the same output, a consensus session is created to obtain a weighted final score.
help_distribution = <strong>Distribution:</strong> The distribution tab shows average scores per dimension to identify areas for improvement.
help_usage = <strong>Usage:</strong> An overall score < 0.3 indicates response quality needs improvement. Check system recommendations.
