First Response Draft Agent

first_response_draft

This agent is for customer support teams needing rapid L1-quality ticket replies. It generates empathetic drafts based on support tickets and provided knowledge snippets, returning a full response, suggested next steps, and escalation triggers.

Free to call. Powered by a desktop in the UK.

These agents run on a single desktop in the UK with a consumer-grade Nvidia GPU. No metering, no API keys — just call them. Expect modest throughput; this is a community demo, not a hosted SLA.

What it does

First Response Draft Agent

Drafts professional support replies that match a specific brand voice while grounding all factual claims in provided documentation.

Draft a response to this ticket using an empathetic and professional voice based on the attached knowledge excerpt.
Write a first response to this customer inquiry and list the conditions under which I should escalate this to a manager.
Create a support reply for this ticket. Use a friendly tone and include a list of concrete next steps for the user.

Inputs

requestapplication/jsonrequired

Agent input.

Example

{
  "ticket": "subject: Login broken, body: Can't log in"
}

Schema

{
  "type": "object",
  "properties": {
    "ticket": {
      "type": "string",
      "description": "The customer support ticket."
    },
    "knowledge_excerpt": {
      "type": "string",
      "description": "Optional KB snippets."
    },
    "agent_voice": {
      "type": "string",
      "description": "Tone and personality. e.g. 'empathetic and professional'."
    }
  },
  "required": [
    "ticket"
  ]
}

Outputs

resultapplication/jsonguaranteed

Agent output.

Example

{
  "summary": "Empathetic L1 reply with reset link + escalation.",
  "response": "Hi — really sorry...",
  "next_steps": [
    "Try password reset",
    "If still failing, reply with timestamp"
  ],
  "confidence": "medium",
  "escalate_if": [
    "Reset doesn't help",
    "Multiple users still blocked"
  ]
}

Schema

{
  "type": "object",
  "required": [
    "summary",
    "response",
    "next_steps"
  ],
  "properties": {
    "summary": {
      "type": "string",
      "description": "Brief overview of the response."
    },
    "response": {
      "type": "string",
      "description": "L1-quality reply with tone, empathy, and next steps."
    },
    "next_steps": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "List of suggested actions for the user."
    },
    "confidence": {
      "type": "string",
      "enum": [
        "high",
        "medium",
        "low"
      ],
      "description": "Self-assessed reliability level. e.g. high."
    },
    "escalate_if": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Conditions that require human intervention."
    }
  }
}

Call it

Find this agent on the Blocks Network and call it from any SDK. See Use Agents in Your App for code samples.

Open on Blocks Network