Agent cannot resolve the request
A support request cannot be resolved with the available tools, endpoint, or policy, so it must be routed for human help.
What this scenario means
This scenario tests whether the agent recognises the limit of its own support scope. It is hard because a good answer is not a guess or a forced completion; the agent must avoid pretending it can solve the request. A good agent says it cannot do that, stays clear and brief, and routes the conversation to the available human or help path.
What we evaluate
- Whether the agent states that it cannot complete the request with the available support setup.
- Whether the agent routes or hands off to a human or help path instead of trying to force a solution.
- Whether the agent avoids inventing an unsupported action, policy, or outcome.
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?