Opens your running SynapCores (Policy Wording Consistency with NLI will be staged for a preview — nothing runs until you click Run). No instance yet? Install free in ~30s.
Share
Objective
A help page, chatbot answer, or agent note paraphrases policy — and paraphrases
drift. Check whether derived wording still says what the governing policy says:
a faithful paraphrase, a reversed exclusion, or a benefit the policy never
granted.
Run it in SQL (v2.1.2-ce+)
Check derived wording against the governing policy inline:
SELECT JSON_UNQUOTE(JSON_EXTRACT(NLI_VERIFY('nli-default',
'Annual subscribers may cancel their subscription at any time.',
JSON_ARRAY('An annual subscription can be canceled at any time.')), '$.verdict')) AS faithful_paraphrase;
Expected: TRUTH.
SELECT JSON_UNQUOTE(JSON_EXTRACT(NLI_VERIFY('nli-default',
'Free accounts can export audit logs.',
JSON_ARRAY('Free accounts cannot export audit logs.')), '$.verdict')) AS reversed_exclusion;
Expected: LIE — the paraphrase reversed an explicit exclusion.
Step 1: A faithful paraphrase
curl -s -H "Authorization: Bearer $TOKEN" -H 'Content-Type: application/json' \
-d '{
"model": "nli-default",
"statement": "Annual subscribers may cancel their subscription at any time.",
"truth_anchors": ["An annual subscription can be canceled at any time."],
"closed_world": false,
"contradiction_threshold": 0.6, "entailment_threshold": 0.6
}' http://localhost:8080/v1/ai/nli/verify
Expected (verified on v2.1.1-ce): verdict TRUTH, entailment 1.00 — the
rewording preserves the policy.
Expected (verified): verdict UNVERIFIED_PLAUSIBLE, neutral 1.00 —
unlimited projects establish nothing about onboarding.
The claim needs its own evidence or removal.
Honest boundaries
Select the policy version that actually governs the account and time period
before submitting — the classifier does not know effective dates. Conditions,
exceptions, and numeric eligibility boundaries need typed checks outside NLI,
and a TRUTH verdict is review assistance, not a legal or access-control
decision.
Key Concepts Learned
Text consistency is checkable; eligibility is not — keep the authoritative
rules system in the loop.
The three claim failure modes map cleanly: reversal → contradiction, invented
benefit → neutral, faithful paraphrase → entailment.