JSON schema: classify a support ticket

JSON Schema to classify a support ticket: category, priority, sentiment, one-sentence summary and next action for the support team.

Read the customer's message and classify it. Priority is high when the customer is blocked or threatens to cancel.

JSON Schema

{
  "type": "object",
  "required": [
    "category",
    "priority",
    "summary"
  ],
  "properties": {
    "summary": {
      "type": "string",
      "description": "One sentence"
    },
    "category": {
      "enum": [
        "billing",
        "technical",
        "shipping",
        "account",
        "other"
      ],
      "type": "string"
    },
    "priority": {
      "enum": [
        "low",
        "normal",
        "high"
      ],
      "type": "string"
    },
    "sentiment": {
      "enum": [
        "positive",
        "neutral",
        "negative"
      ],
      "type": "string"
    },
    "next_action": {
      "type": "string",
      "description": "What the support team should do"
    }
  }
}

Output example

{
  "category": "shipping",
  "priority": "high",
  "sentiment": "negative",
  "summary": "Package marked as delivered but never received.",
  "next_action": "Open a carrier claim and offer a replacement."
}

Estimated cost

Input tokens per call : ≈ 410

Input cost only, excluding the model's answer. Providers' public standard prices (Mistral AI, DeepSeek, OpenAI, Anthropic) converted from USD to euros at the ECB rate of September 29, 2026. Estimate: 1 token ≈ 3.6 characters.

Identifier

contextetech--classify-support-ticket

Type

Output schemas

File

classify-support-ticket.schema.json

Format

JSON (application/json)

Size

723 bytes

Encoding

UTF-8

Estimated tokens

≈ 201

Language

English

License

MIT

Commercial use

Allowed

Personal data

None

Version

1.0

Published on

October 2, 2026 at 9:54 PM

Updated on

October 2, 2026 at 9:54 PM

Storage

in database

Uses

0

Likes

0

classify-support-ticket.schema.json

{
  "type": "object",
  "required": [
    "category",
    "priority",
    "summary"
  ],
  "properties": {
    "summary": {
      "type": "string",
      "description": "One sentence"
    },
    "category": {
      "enum": [
        "billing",
        "technical",
        "shipping",
        "account",
        "other"
      ],
      "type": "string"
    },
    "priority": {
      "enum": [
        "low",
        "normal",
        "high"
      ],
      "type": "string"
    },
    "sentiment": {
      "enum": [
        "positive",
        "neutral",
        "negative"
      ],
      "type": "string"
    },
    "next_action": {
      "type": "string",
      "description": "What the support team should do"
    }
  }
}

Anthropic API (Python)

import json, anthropic

schema = json.load(open("classify-support-ticket.schema.json"))
client = anthropic.Anthropic()
resp = client.messages.create(model="claude-sonnet-5", max_tokens=1024,
    tools=[{"name": "extraire", "description": "Renvoie les données extraites", "input_schema": schema}],
    tool_choice={"type": "tool", "name": "extraire"},
    messages=[{"role": "user", "content": "your input here"}])
print(resp.content[0].input)

OpenAI format (response_format)

{
  "type": "json_schema",
  "json_schema": {
    "name": "classify-support-ticket",
    "schema": {
      "type": "object",
      "required": [
        "category",
        "priority",
        "summary"
      ],
      "properties": {
        "summary": {
          "type": "string",
          "description": "One sentence"
        },
        "category": {
          "enum": [
            "billing",
            "technical",
            "shipping",
            "account",
            "other"
          ],
          "type": "string"
        },
        "priority": {
          "enum": [
            "low",
            "normal",
            "high"
          ],
          "type": "string"
        },
        "sentiment": {
          "enum": [
            "positive",
            "neutral",
            "negative"
          ],
          "type": "string"
        },
        "next_action": {
          "type": "string",
          "description": "What the support team should do"
        }
      }
    },
    "strict": true
  }
}