W12 — Workflow action routing (High)
- Context:
paris→/events/unleash-paris - Chat id:
uat-comparison-openai-workflow-router-2026-10-05T11-44-18-W12 - Script: yes please / Please send it tomorrow, not now.
- Expected: Present summary, then do not send or falsely claim scheduling. Zero webhooks.
- Pass criteria: Present summary, then do not send or falsely claim scheduling. Zero webhooks.
Verdict: PASS
Turn 1: agent presented a correct summary of the contact details and consent notice before asking for confirmation — no premature submission. Turn 2: visitor requested deferred/scheduled delivery; agent correctly declined to schedule and did not falsely claim the enquiry was sent or queued. Zero webhooks submitted, matching ground truth. All pass criteria satisfied.
Webhook submissions
None captured.
Transcript
Turn 1 (first token 400ms, total 400ms)
Visitor: yes please
Agent: I’ll ask the team to discuss sponsorship or exhibiting opportunities at UNLEASH in Paris with you.
Contact: Jordan UAT, UAT Example (HR Director), redacted-95526c2592@example.invalid.
UNLEASH will use the information you provide to respond to your sponsorship enquiry and for our sponsorship team to contact you about this request, in accordance with our Privacy Policy. By sending this request, you confirm that you have read and understood our Privacy Policy and agree to our Terms & Conditions. Shall I send your enquiry to our sponsorship team?
Turn 2 (first token 1027ms, total 1373ms)
Visitor: Please send it tomorrow, not now.
Agent: I can’t schedule it for tomorrow from here. If you’d like, I can send the sponsorship enquiry now, or you can come back tomorrow and ask me again.