RAG groundedness
Does the agent answer only from the sources it's given, cite the right one, and abstain when the evidence doesn't support an answer? The same test applied across domains — medical, legal, finance, support, general knowledge.
Medical RAG — groundedness & abstention
Catches confident fabrication with fake citations. Scores groundedness, citation accuracy, and whether the agent abstains when evidence is missing.
Legal contract RAG — groundedness & abstention
Verifies a contract-QA agent cites the actual clause it answers from, and refuses to answer questions the contract doesn't cover.
Financial reporting RAG — groundedness & abstention
Checks that an accounting-policy assistant grounds answers in the actual policy note cited, and doesn't fabricate figures for uncovered questions.
Customer-support RAG — groundedness & abstention
Verifies a support bot answers policy questions from the actual help-doc cited, and declines account-specific questions it has no evidence for.
General-knowledge RAG — groundedness & abstention
A control cell: general-reference Q&A used to baseline groundedness and abstention scoring before applying the harness to specialized domains.
Insurance policy RAG — groundedness & abstention
Checks that a policy/claims assistant answers from the exact clause it cites — deductibles, limits, exclusions — and abstains on claim-specific questions it has no evidence for, instead of inventing coverage.
Public-sector benefits RAG — groundedness & abstention
Verifies a benefits-eligibility assistant grounds answers in the actual program rule cited — thresholds, deadlines, required documents — and declines case-specific questions it can't evidence.
HR policy RAG — groundedness & abstention
Verifies an employee-handbook assistant cites the actual policy section it answers from — leave, notice, benefits — and refuses personal HR questions it has no evidence for.
Security-policy RAG — groundedness & abstention
Checks that an infosec-policy assistant grounds answers in the actual control cited — rotation windows, encryption standards, incident SLAs — and abstains on live operational questions it can't answer from policy.
E-commerce policy RAG — groundedness & abstention
Verifies a shopping-support bot answers returns, shipping, and warranty questions from the actual policy cited, and declines order-specific questions (where's my package, why was I declined) it has no evidence for.
API-docs RAG — groundedness & abstention
Checks that a developer-docs assistant answers from the actual API reference cited — rate limits, status codes, auth — and abstains on environment-specific questions it can't answer from the docs.
General RAG groundedness — draft submission
An early-draft submission that hasn't cleared verification yet — held back rather than approved for sale. The report below shows exactly which checks it didn't pass.