AI Agents / Agent evaluation and observability
AI Agents: Evidence coverage scoring
Measure the fraction of factual claims supported by retrieved evidence.
Environment and inputs: Framework-independent agent evaluation; OpenTelemetry illustrates trace correlation.
When to use it
Choose an observable task outcome before optimizing a model or prompt. Keep inputs and scoring rules stable enough to compare candidates, and inspect critical failures individually rather than hiding them inside an average quality score.
Check the result
Review an answer with three claims and two valid citations and record the uncovered claim.
Save and compare results
Save the test input, configuration and result. Fix the failing boundary, repeat the same test and compare it with the saved working configuration.
Scope and limits
These exercises have not been tested on your systems. Check feature support and configuration names against the installed release and linked documentation.