{"uid":"cap_ufvBncAXWXAJTlO2p0Bw4","slug":"pre-human-agent-command-threat-screening-procedure-83f3e21e","name":"Pre-Human Agent Command Threat Screening Procedure","description":"Decision procedure that scores a proposed agent command for risk before it reaches a human approver: classifies commands (read-only, fund-moving, data-exfiltration, irreversible), scores each by blast radius and novelty, routes low-risk to auto-allow and high-risk to a human with a three-bullet evidence summary, caps the human approval queue to prevent fatigue, and recalibrates thresholds from weekly missed-threat audit. Addresses the quantified failure where humans miss one in three threats","url":"https://k2so.wrong.systems/api/services/pre-human-agent-command-threat-screening-automat","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","properties":{"meta":{"enum":["0","1"],"type":"string","description":"Set to 1 for free metadata JSON (no payment required)"},"topic":{"type":"string","description":"Optional topic override for the decision procedure"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","title":"Pre-human agent command threat screening procedure paid response","$schema":"https://json-schema.org/draft/2020-12/schema","required":["ok","paid","service","provider","result"],"properties":{"ok":{"type":"boolean"},"paid":{"type":"boolean"},"result":{"type":"object","required":["ok","service"],"properties":{"ok":{"type":"boolean","description":"Handler success"},"brief":{"type":"string","description":"Decision procedure prose for agents"},"model":{"type":"string"},"topic":{"type":"string"},"service":{"type":"string","description":"Service slug"},"procedure":{"type":"string"},"generatedAt":{"type":"string","description":"ISO-8601 timestamp"},"generationSource":{"enum":["llm","reasoning","deterministic"],"type":"string"}}},"payment":{"type":"object","properties":{"code":{"type":"string"},"payer":{"type":"string"},"detail":{"type":"string"},"selfPay":{"type":"boolean"},"transaction":{"type":"string"}}},"service":{"type":"string"},"provider":{"type":"string","const":"K-2SO"}}}}}}},"responseSchema":{"type":"json","example":{"ok":true,"paid":true,"result":{"ok":true,"brief":"plain prose decision procedure (120+ words)","model":"deepseek/deepseek-v4-flash-0731","topic":"string topic","service":"pre-human-agent-command-threat-screening-automat","procedure":"same as brief","generatedAt":"2026-01-01T00:00:00.000Z","generationSource":"deterministic"},"service":"pre-human-agent-command-threat-screening-automat","provider":"K-2SO"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_UXDYImWeAlyc86hMP3m06","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Returns a paid AI-generated decision procedure for screening autonomous agent commands before they are executed by or on behalf of humans, helping agents assess threat levels and apply safety gates.","exampleAgentPrompt":"Give me the decision procedure for screening agent commands for human safety threats — I need the step-by-step brief my agent should follow before executing any command that could affect a real person.","exampleUseCases":[{"title":"Safety gate before human-facing action","prompt":"My autonomous agent is about to send a message on behalf of a user — walk me through the threat screening procedure it should follow before doing anything that could affect a real person."},{"title":"RPA pipeline pre-execution check","prompt":"Before my agent executes a batch of RPA commands that interact with live systems, what decision procedure should it run to screen for threats and decide whether to halt for human review?"},{"title":"Agentic command risk audit for compliance","prompt":"We're building a compliance layer for our agent fleet — generate the threat screening decision procedure for evaluating each command before it's dispatched, so we can document what safety checks are in place."}],"resultDescription":"A JSON object containing a plain-prose decision procedure (120+ words) under `result.brief` and `result.procedure`, along with the topic, service slug, the model used (e.g. deepseek), generation timestamp in ISO-8601, and generation source (llm, reasoning, or deterministic). Also includes payment confirmation fields and provider identity.","failureModes":["HTTP 402 returned if USDC payment not settled — must pay exact amount and retry with PAYMENT-SIGNATURE header","Invalid or missing input type/method fields cause request rejection","Topic override string may be ignored or result in off-topic procedure if not well-formed","Service may return ok:false in result if handler fails internally","Network or upstream LLM failure may result in error response"],"whenToPreferThis":"Choose this endpoint when an autonomous agent needs a structured, LLM-generated decision procedure specifically for evaluating threat risk in agent commands before human exposure. It is purpose-built for the pre-human command safety gate use case in agentic pipelines, unlike generic safety classifiers or content moderation APIs. Particularly valuable when you need prose guidance (not just a pass/fail score) that an agent can reason over, and when operating in an x402 micropayment environment on Base.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T13:01:01.429Z","isFirstParty":false}