RAG source match: deterministic LLM output check

Terms in output must appear in input or RAG source text.

Terms in output must appear in input or RAG source text.

This page is the SEO reference for the rag_source_match validator. Configure it on an agent in the dashboard or via the agents API. Full catalog: validators.

What it checks

Terms in output must appear in input or RAG source text.

FieldValue
Rule IDrag_source_match
Packcore
CategoryRAG
Default severityerror
Default on_failblock

Config notes

Attach the rule to an agent, set severity and on_fail, then start in shadow mode before enforce. Pack core must be allowed on your plan.

Pass / fail example

Pass: output satisfies the encoded contract for this rule (shape, pattern, or checksum as configured).

Fail: output violates the contract. ValGuard returns a validation failure with this rule ID when on_fail is block or reask.

Exact fixtures depend on your field paths and thresholds. Use the dashboard tester or validate LLM output.

on_fail behaviours

ModeEffect
blockRequest fails closed; next step should not run
reaskProxy may retry the model once within plan limits; buffers stream
warn / logTraffic continues; audit still records the evaluation
shadow agentWould-block logged; response still delivered

Prefer fail-closed for money and PHI paths.

Performance

Engine timing: 901 ns engine p50 (snapshot). HTTP path and model time dominate end-to-end latency. See methodology. Numbers are ValGuard's own measurements on published hardware snapshots.

Related

Next step

Quickstart. Attach rag_source_match in shadow on one agent, then enforce.