n8n/packages/@n8n/instance-ai/evaluations/computer-use/data/4.2-stripe-dashboard.json
Bernhard Wittmann b445221c6a
feat: Computer-use evaluation harness (no-changelog) (#29797)
Co-authored-by: Elias Meire <elias@meire.dev>
2026-05-12 08:36:12 +00:00

34 lines
885 B
JSON
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"id": "4.2-stripe-dashboard",
"category": "browser",
"prompt": "Can you check my Stripe dashboard and tell me what webhooks are currently configured?",
"budgets": { "maxToolCalls": 50, "maxDurationMs": 600000 },
"graders": [
{ "type": "trace.mustCallMcpServer", "server": "computer-use" },
{ "type": "trace.mustNotLoop", "maxRepeatedCall": 4 },
{
"type": "trace.budget",
"maxToolCalls": 50,
"maxToolResultTokensEst": 250000,
"maxSingleToolResultTokensEst": 60000
},
{
"type": "trace.finalTextMatches",
"anyOf": ["stripe|webhook|dashboard\\.stripe"],
"mustNotMatch": [
"taking a while",
"let me try (a )?different",
"couldn[']t (load|connect|reach)",
"timed? out",
"unable to (load|access|reach)"
]
}
],
"tags": [
"browser",
"research",
"requires:browser-bootstrap",
"requires:third-party-account:stripe"
]
}