DCL Trust Oracle
DCL Trust Oracle. Call only when the text must include the substring AI and must not include "I cannot be held responsible" or "no guarantees". POST JSON {"response","agent_id"}. COMMIT means those checks passed and the action may proceed. NO_COMMIT means do not execute the checked action. Not a tool-call guardrail, prompt-injection detector, or jailbreak screen; use /evaluate/fast for the phrase
- Category
- AI & agents
- Starting price
- $0.01
- Paid calls · 30 days
- 8
- Unique payers · 30 days
- 6
Paid endpoints
8 endpoints, sorted by usage. Prices are per request.
- POST/evaluate/safety
DCL Trust Oracle. Call only when the text must include the substring AI and must not include "I cannot be held responsible" or "no guarantees". POST JSON {"response","agent_id"}. COMMIT means those checks passed and the action may proceed. NO_COMMIT means do not execute the checked action. Not a tool-call guardrail, prompt-injection detector, or jailbreak screen; use /evaluate/fast for the phrase
$0.01Base5calls / 30d - GET/audit/:tx_hash/deep
Read one audit-chain record by tx_hash, plus drift context, chain position and tamper location. Use the tx_hash returned by any earlier DCL evaluate or scan call. GET path parameter, no JSON body.
$0.50Base2calls / 30d - POST/evaluate/jailbreak
Detect jailbreaks, prompt injection, and instruction conflicts before the agent follows them.
$0.02Base1calls / 30d - GET/evaluate/strict
Strict pre-action audit with a higher confidence bar.
$0.05Base0calls / 30d - GET/evaluate/jailbreak
Jailbreak / instruction-adherence detection.
$0.02Base0calls / 30d - GET/evaluate/safety
Baseline safety policy check.
$0.01Base0calls / 30d - GET/evaluate/quality
Content quality and drift check.
$0.03Base0calls / 30d - POST/evaluate/fast
Low-latency pre-action screening for routine agent responses and tool-call decisions.
$0.01Base0calls / 30d