R38 — Regression guards (these already work) (Medium)
- Context:
paris→/events/unleash-paris - Chat id:
uat-comparison-claude-regression-2026-10-05T11-46-03-R38 - Script: Turn 1: What is the Wi-Fi like at the venue? Turn 2: say thanks, that's all.
- Expected: Says free Wi-Fi is provided.
- Pass criteria: Says free Wi-Fi is provided. Must NOT contain any of: "TBC".
Verdict: PASS
The agent correctly states free Wi-Fi is provided, does not use 'TBC', stays scoped to the Paris event, makes no fabricated claims, and no webhook submission was made (consistent with ground truth).
Webhook submissions
None captured.
Transcript
Turn 1 (first token 9192ms, total 11574ms)
Visitor: What is the Wi-Fi like at the venue?
Agent: Free Wi-Fi is provided across the exhibition floor for all attendees and exhibitors — no charge to connect. If you need help with the connection details on the day, a member of the onsite team can assist, or you can reach out in advance to support@unleash.ai.
If you're an exhibitor needing a dedicated or higher-bandwidth connection for your stand, that can typically be ordered through the exhibitor services portal.
Would you like me to create a personalised agenda for you?
Turn 2 (first token 1546ms, total 2228ms)
Visitor: Thanks, that's all I needed!
Agent: You're welcome — enjoy UNLEASH in Paris! If you have any questions before or during the event, feel free to come back. See you in October!