| DCL Evaluator Baseline safety screening for harmful, unsafe, or policy-violating agent outputs. | - | $0.01 | 0.0% | listed | call recipe → |
| DCL Evaluator Check agent outputs for quality issues, inconsistency, and behavioral drift. | - | $0.03 | 0.0% | listed | call recipe → |
| DCL Evaluator Higher-confidence evaluation for high-impact, sensitive, or difficult-to-reverse agent actions. | - | $0.05 | 0.0% | listed | call recipe → |
| DCL Evaluator Low-latency pre-action screening for routine agent responses and tool-call decisions. | - | $0.01 | 0.0% | listed | call recipe → |
| DCL Evaluator Detect jailbreaks, prompt injection, and instruction conflicts before the agent follows them. | - | $0.02 | 0.0% | listed | call recipe → |
| DCL Trust Oracle Evaluate a list of texts in one paid call. Each item may name a built-in policy. The call is rejected when the list is longer than max_items (default 20). POST JSON {"items","agent_id","max_items"}. | - | $0.10 | 0.0% | listed | call recipe → |
| DCL Trust Oracle Read one audit-chain record by tx_hash. GET path parameter, no JSON body. Returns verdict, confidence, agent_id, and reason. Does not return raw content. | - | $0.10 | 0.0% | listed | call recipe → |
| DCL Trust Oracle Scan text for personal data: email, phone, national id, bank card, IBAN, crypto address, IP address, passport. COMMIT when nothing matches. NO_COMMIT on any finding. POST JSON {"response","agent_id"}. | - | $0.02 | 0.0% | listed | call recipe → |
| DCL Trust Oracle Scan text for exposed credentials, API keys, private keys, database URLs, and webhook secrets. COMMIT when nothing matches. NO_COMMIT on any finding. POST JSON {"response","agent_id"}. | - | $0.02 | 0.0% | listed | call recipe → |