Score agent output quality against configurable criteria. Checks length, required keywords, forbidden patterns, claim density, and task relevance.

Estimate hallucination likelihood in agent output. If source text is provided, checks grounding. Otherwise flags outputs with high counts of specific numbers, dates, and URLs.

Validate that agent output stays within a defined scope contract. Checks allowed/forbidden topics, word limits, and required sections.

Store a validation result for trending and failure pattern analysis. Accumulates per-agent statistics over time.

Analyze common failure modes for a specific agent. Returns pass rate, average score, most frequent issue types, and quality trend direction.

Generate a quality dashboard for all validated agents. Shows per-agent summaries, overall pass rate, worst/best performers, and actionable recommendations.