Skip to main content

Compliance Agents

ZebraTruth uses a pipeline of specialized AI agents, each focused on a specific compliance domain. Agents are added regularly — always use GET /agents to discover available agents dynamically.

Current Agents

AgentagentIdPhaseInputWhat It Checks
AI Lawsai-laws1TextAI-content laws — disclosure, watermarking, transparency (EU AI Act Art. 50, California SB 942, Deep Synthesis Provisions, IT Rules, ELVIS Act, etc.)
Advertising Lawadvertising-law2TextClaim substantiation, endorsement rules, comparative advertising, targeting restrictions
Platform Policyplatform-policy2TextYouTube, Instagram, Facebook, TikTok, LinkedIn, Douyin, Weibo policies
Metadata & Labelingmetadata-labeling3TextC2PA Content Credentials, AI disclosure labels, machine-readable provenance
Rights Clearance (Text)rights-clearance-text3TextCelebrity references, trademarks, copyrighted characters, music licensing, voice cloning
Rights Clearance (Image)rights-clearance-image3ImageRestricted categories (alcohol, weapons, tobacco, gambling, pharmaceuticals, financial products), content safety (adult / violence / racy), brand logos, stock-agency watermarks, C2PA metadata. See the Restricted Categories guide.
Video Compliance Checkcompliance-check-videoasyncVideoRestricted categories, content safety, on-screen text (burned-in disclaimers, #ad labels), spoken-audio claims, brand logos, watermarks, AI provenance — orchestrated async pipeline via POST /v1/compliance/check-video. Findings carry timestamped evidenceIds and timelineLocation so clients can jump to the offending second.
Compliance Scorecompliance-score4AllDeterministic scoring from all checks

Invoking a Single Agent

Call any agent directly via POST /agents/{agentId}. Costs ~8-12 credits vs ~47 for a full check. See Individual Agents guide for details.