Observability & Evaluation · Data artifact

Balanced Scorecard Specification

Data artifactObservability & EvaluationObservability & Evaluationarc:BalancedScorecardSpec

A specification of acceptable ranges for 4-6 complementary agent success metrics (e.g., completion, CSAT, NPS, CES, deflection) that must all be met simultaneously rather than maximising any single metric.

Responsibility. Declares the acceptable range for each complementary success metric of an agent.

Also known as: Balanced scorecard, Multi-dimensional success targets

Direct neighbourhood (hover for relationship types)

Relationships

configures structural

is read by dependency

Metrics Dashboard abstract Ch8.4

Design guidance

SHOULD define acceptable ranges, not maximisation targets, for 4-6 complementary metrics spanning completion, satisfaction, efficiency, quality and safety.
SHOULD make trade-offs explicit (e.g., higher completion may need more latency; more escalation of ambiguous cases may lower deflection but raise satisfaction).

Quantitative guidance

As stated by the sources; verify before use.

Example customer-service scorecard: task completion >=90% (not maximised), CSAT >=80%, NPS >=+30, CES <=3.0, deflection rate 85-95% (Ch8.4).

Classification

Patterns: Balanced scorecardAcceptable ranges instead of maximisation
Quality attributes: Maintainability (ISO/IEC 25010)Interaction capability (ISO/IEC 25010)Cost efficiency
Risks mitigated: Pathological single-metric optimizationMetric gaming

Sources

Ch8.4: T. Nguyen, "Success Metrics and Multi-Dimensional Measurement," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 8.4. ISBN: 9798244538229.