{"uid":"cap_FAkwIWjHNmo46k98epLIX","slug":"tradepilot-content-safety-review-4900da83","name":"TradePilot Content Safety Review","description":"Review supplied marketing or social copy for policy-risk language: unverified health or medical claims, financial guarantees, discriminatory language, or other content likely to be rejected by ad or social platforms. Return a verdict, flagged spans quoting the exact risky text, and a brief reason for each flag. Do not rewrite the copy unless asked. Uses buyer-supplied information only; no external research or outbound actions. Returns a draft for human review.","url":"https://www.tradepilotusa.com/api/agent-commerce/v1/services/content_safety_review/execute?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"brief":{"type":"string","maxLength":12000,"minLength":10},"audience":{"type":"string","maxLength":500},"source_text":{"type":"string","maxLength":32000,"minLength":20}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.25","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":"$0.25/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.25","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.25","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_kgJf7zdvT7gfIddgfciMp","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.25","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Reviews marketing or social copy for policy-risk language including unverified health/medical claims, financial guarantees, discriminatory language, and other content likely to be rejected by ad or social platforms.","exampleAgentPrompt":"Can you review this Facebook ad copy for any language that might get it rejected — especially any health claims or financial guarantees? The copy is: 'Our supplement cures chronic pain in 7 days, guaranteed to double your energy or your money back.' It's targeted at adults 35–60 with chronic fatigue.","exampleUseCases":[{"title":"Pre-screen Google Ads before submission","prompt":"Before I submit this Google ad, can you check it for anything that might get it rejected? The copy says: 'Earn $500/day from home — guaranteed returns with our trading system. No experience needed!' It's aimed at first-time investors."},{"title":"Audit health supplement landing page copy","prompt":"I need you to review my supplement landing page copy for any claims that could violate FDA or ad platform rules. The copy includes lines like 'clinically proven to reverse diabetes' and 'doctors recommend our product.' Flag anything risky."},{"title":"Compliance check for financial services ad","prompt":"Can you scan this financial services ad copy for any guarantee language or misleading claims before we run it on Meta? The copy is: 'Our fund has never lost money — join thousands who achieved financial freedom through our zero-risk investment strategy.' Audience is high-net-worth individuals over 50."}],"resultDescription":"Returns a policy-risk verdict (pass/flag), a list of flagged text spans quoting the exact risky language found in the source text, and a brief reason for each flag explaining which policy category it risks violating. The response is a draft for human review and does not rewrite the copy.","failureModes":["Source text too short (under 20 characters) or too long (over 32,000 characters) causes validation error","Brief too long (over 12,000 characters) causes rejection","No policy-risk language found returns a clean verdict with no flags","Ambiguous or borderline language may not be flagged if it falls below the risk threshold","Input-only analysis — no external research means platform-specific policy updates not reflected in real time"],"whenToPreferThis":"Choose this endpoint when you need a fast, structured pre-submission audit of ad or social copy for platform policy compliance, particularly for health/medical claims, financial guarantees, or discriminatory language — without rewriting the copy. Prefer this over general-purpose LLM review when you need machine-readable flagged spans with exact quoted text and structured reasons, and when you want a deterministic, buyer-supplied-only analysis with no external research or outbound calls.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-02T04:15:41.208Z","isFirstParty":false,"canonicalSlug":"tradepilot-content-safety-review-4900da83"}