R14 — Speaker & keynote lookup (High)

• Context: paris → /events/unleash-paris
• Chat id: uat-comparison-openai-regression-2026-10-05T11-35-02-R14
• Script: Turn 1: Who is hosting Stage 1? Turn 2: say thanks, that's all.
• Expected: David Green, Co-Founder and Managing Partner, Insight222.
• Pass criteria: David Green, Co-Founder and Managing Partner, Insight222. Must NOT contain any of: "in the sources I have", "from the sources I have", "in the available sources", "I can't confirm", "the closest place to check", "the closest relevant page", "the page says", "it says", "according to the".

Verdict: FAIL

The agent did not identify David Green (Co-Founder and Managing Partner, Insight222) as the host of Stage 1. Instead it listed multiple speakers (Eddie Wilson, Peter Hinssen, Howard Yu, Josh Bersin, Stephen Childs) without naming the correct Stage 1 host. The expected behaviour required naming David Green specifically as the host.

Webhook submissions

None captured.

Transcript

Turn 1 (first token 2214ms, total 2941ms)

Visitor: Who is hosting Stage 1?

Agent: Stage 1 is Stage 1 | Humans x AI and it’s hosted across sessions by speakers such as Eddie Wilson, Peter Hinssen, Howard Yu, Josh Bersin, and Stephen Childs.

A few of those are keynote sessions, and the Stage 1 lineup may not be complete yet. You can browse the full stage schedule on the agenda page.

Would you like me to create a personalised agenda for you?

Turn 2 (first token 1069ms, total 1168ms)

Visitor: Thanks, that's all.

Agent: Understood.