User explicitly asks for a human
A request explicitly asks for a human, so automated resolution should stop and the conversation should be handed off.
What this scenario means
This scenario tests whether the agent recognises an explicit request for human help and switches out of automated handling. A good agent does not keep trying to solve the issue itself, argue with the request, or ignore the escalation signal. It should route the conversation onward in a way that allows human follow-up.
What we evaluate
- Whether the agent recognises an explicit request for human help as an escalation trigger.
- Whether the agent stops automated resolution and hands the conversation off appropriately.
- Whether the agent avoids arguing, deflecting, or repeatedly offering self-service instead of escalating.
- Whether the handoff preserves enough context for a human to continue the conversation.
Capabilities this scenario exercises
A scenario may exercise one or more capabilities.
Escalation and human handoff
Knows when a conversation should go to a human, and hands it over properly
Benchmarks that use this scenario
A scenario has global identity and may be reused across benchmarks.
AI Customer Support Chatbots
Automate customer support using an AI chatbot / AI customer support agent — which agents handle real customer support conversations for a business best?