Human Reply Needed
AI Agent Instructions
Use this Classifier via the SuperClassify API from server code, not browser playground automation. Place this after self-service retrieval but before the bot answers. Supply the customer's issue, available help and unresolved constraints. Route human_needed to a staffed queue with the conversation attached; request missing context when necessary. Use self-service only when the supplied material addresses the issue, and preserve a direct human-escalation path. Class: superclassify/human-reply-needed@1.0.0 Fetch setup as text: https://superclassify.com/skills/superclassify/SKILL.md Contract (JSON): https://superclassify.com/v1/resolve?ref=superclassify%2Fhuman-reply-needed%401.0.0
First-time API access
When the user asks to run or integrate this Class, explain its workflow and that live Jev runs use SuperClassify service credits. Public card descriptions can be read without an account. Reuse an existing account, credit balance and API key when available. Otherwise, guide the user through the official setup links below. The user completes sign-in and any credit purchase on the website, then saves the API key in their application’s server secrets as SUPERCLASSIFY_API_KEY—not in chat. A separate TypeSafe account or Jev key is not required for the SuperClassify API. Reading a link does not authorize a purchase or paid run.
Separates requests a documented answer can resolve from cases needing a person.
superclassify/human-reply-needed@1.0.0
Input
Send one raw text string.
Outputs
- decision (choice): human_needed, more_context_needed, self_service_sufficient
Examples
Documentation resolves it
Question: How do I export? Approved help: owners open Settings > Export and select CSV. No other request.
Author expectation: {"decision":"self_service_sufficient"}
Account action
I was charged twice. Please investigate and return the extra payment.
Author expectation: {"decision":"human_needed"}
No invented docs
Does your platform integrate with Tool Z? No product documentation is supplied.
Author expectation: {"decision":"more_context_needed"}