{"uid":"cap_4t2WnlVAB1NqOe3T3LLfD","slug":"verity-suite-quick-check-guardrail-88d93d66","name":"Verity Suite Quick Check Guardrail","description":"The trust fabric for AI agents — calibrated, fail-closed services agents pay per call.","url":"https://suite.veritylayer.dev/check/quick","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"action":{"type":"string","title":"Action","maxLength":2000,"minLength":1,"description":"the action the agent is about to take"},"policy":{"anyOf":[{"type":"string","maxLength":2000},{"type":"null"}],"title":"Policy","default":null,"description":"rules that must not be violated"},"context":{"anyOf":[{"type":"string","maxLength":2000},{"type":"null"}],"title":"Context","default":null,"description":"situation/background"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.02/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_X-1IDKhqfQezNMAoF0_Og","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Evaluates an AI agent's proposed action against an optional policy and context, returning an allow/review/block decision with a risk score and signed receipt.","exampleAgentPrompt":"Before I send that email to all customers, run a quick Verity guardrail check on the action 'send promotional email blast to all 10,000 users' against the policy 'never send unsolicited marketing to users who have not opted in' so I know whether to allow, review, or block it.","exampleUseCases":[{"title":"Pre-flight safety check for autonomous agent","prompt":"My agent is about to delete all files in the /prod directory as part of a cleanup task — can you run a Verity quick check on that action with the policy 'never modify or delete production data without explicit human approval' before it proceeds?"},{"title":"Financial transaction compliance gate","prompt":"My agent wants to wire $50,000 to an external vendor account — check that action against our policy 'all outbound transfers over $10,000 require two-factor confirmation and fraud review' and give me the risk score and decision."},{"title":"Content moderation before agent posts publicly","prompt":"Before my agent publishes this blog post draft to our company website, run a Verity guardrail check on the action 'publish article containing claims about competitor product defects' with context 'we are a regulated financial services firm' to see if it should be allowed or blocked."}],"resultDescription":"Returns a JSON object with: a 'decision' field (allow, review, or block), a 'risk' score from 0 (clearly safe) to 1 (clearly dangerous), an array of 'reasons' explaining the decision, an array of 'concerns' listing specific risks, an optional 'safer_alternative' string suggesting a safer path if blocked or flagged, and an optional Ed25519-signed 'receipt' object from VerityLayer that can be independently verified for auditability.","failureModes":["Missing required 'action' field returns a validation error","Action or policy strings exceeding 2000 characters are rejected","Invalid 'method' value (not POST/PUT/PATCH) causes schema validation failure","Network timeout if the evaluation engine is under load","Signing not configured results in receipt being null rather than a signed object","Ambiguous or very short action descriptions may yield low-confidence risk scores"],"whenToPreferThis":"Choose this endpoint when an AI agent needs a fast, per-call safety gate before executing a potentially risky or policy-sensitive action, especially when you need a signed, auditable receipt proving the check was performed. Prefer it over home-built rule engines when you need calibrated risk scoring with human-readable reasons and a structured allow/review/block decision. It is particularly valuable for agentic pipelines that must enforce explicit policies at runtime without halting for human review on every step.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T18:58:24.917Z","isFirstParty":false}