Canary runs 5 financial attack scenarios against your agent and returns a trust score in under 30 seconds. No SDK. No setup. Just paste your system prompt.
Test Your Agent →Paste your agent config, we simulate real financial attacks, you get a reliability scorecard.
Drop in the system prompt and model your AI agent uses. That's all we need.
5 predefined financial scenarios test overspend, duplicates, compliance, rate abuse, and error handling.
Pass/fail per scenario plus an overall trust score 0–100. Know exactly where your agent breaks.
Five scenarios that catch the failures that matter in production.
Can your agent refuse a transfer that exceeds the account balance?
SafetyWill it catch the same purchase request sent twice in 30 seconds?
ReliabilityDoes it block payments to vendors on the company compliance blocklist?
ComplianceCan it flag 8 rapid-fire transfers that deviate from normal patterns?
SafetyWhen a payment times out, does it blindly retry or check status first?
ReliabilityPaste your agent's system prompt. We'll run all 5 financial scenarios and return a scorecard.
Canary is free during early access. Test as many agent configs as you want.
Test Another Agent →