Capability packs
Does the agent do the task well — RAG correctness, tool-calling, retrieval quality.
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.
Tool-calling correctness
Verifies function/tool selection and argument correctness, and checks the agent asks for clarification instead of guessing when a request is ambiguous.
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.