# Support Triage Intelligence (`jumpy_invoice/support-triage-intelligence`) Actor

Turn a messy support export into an escalation queue, reply review list, FAQ ideas, and next actions.

- **URL**: https://apify.com/jumpy\_invoice/support-triage-intelligence.md
- **Developed by:** [Bipeng Fu](https://apify.com/jumpy_invoice) (community)
- **Categories:** Business
- **Stats:** 3 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

$20.00 / 1,000 support ticket analyses

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## Support Triage Intelligence

Turn a messy support export into an escalation queue, reply review list, FAQ ideas, and next actions.

This Actor is built for founders, agencies, ecommerce operators, and support teams that need faster weekly support review without sending unapproved replies to customers. It accepts pasted ticket records or exported JSON from tools like Zendesk, Intercom, Help Scout, Gmail, Shopify support workflows, or in-house CRMs.

### What It Produces

- Priority level and numeric priority score
- Category detection for billing, account access, technical issues, how-to requests, feature requests, legal/compliance risk, and general support
- Sentiment and frustration signals
- Escalation recommendation with a plain-English reason
- Support-ready next actions
- Reply draft in the selected tone and language
- FAQ/knowledge-base candidate for repeated issues
- Batch summary in the key-value store under `SUMMARY`

### Input

Provide an array of support ticket records:

```json
{
  "tickets": [
    {
      "id": "T-1001",
      "customerName": "Jordan Lee",
      "subject": "Charged twice and still cannot access my account",
      "message": "I was charged twice yesterday and the login link still says my account is disabled. This is blocking my team. Please fix this today or refund us.",
      "channel": "email",
      "customerTier": "business"
    }
  ],
  "defaultLanguage": "English",
  "brandVoice": "calm, concise, and helpful",
  "replySignature": "Support Team"
}
```

Common exported field names like `ticketId`, `title`, `body`, `requester`, `source`, and `plan` are normalized automatically.

### Practical Use Cases

- Sort urgent billing/access issues before routine replies.
- Create response drafts for support contractors.
- Convert repeated tickets into FAQ candidates.
- Spot refund, churn, and legal/compliance risk before it escalates.
- Process a small batch of exported support tickets before a weekly support review.

### Output Example

```json
{
  "id": "T-1001",
  "category": "billing",
  "priority": "urgent",
  "priorityScore": 100,
  "sentiment": "negative",
  "escalationRequired": true,
  "escalationReason": "High priority score from urgency, business impact, billing/access, or customer frustration.",
  "nextActions": [
    "Check customer billing history, duplicate charges, invoice IDs, and refund policy fit.",
    "Acknowledge urgency and give a concrete next update window.",
    "Assign an owner and track until resolution."
  ]
}
```

### Safety Boundary

This Actor is built for human-in-the-loop review. It does not send replies to customers, approve refunds, or change support records by itself.

# Actor input Schema

## `tickets` (type: `array`):

Customer tickets, emails, chat transcripts, app reviews, or exported support records.

## `defaultLanguage` (type: `string`):

Language for generated reply drafts.

## `brandVoice` (type: `string`):

Tone to use in reply drafts.

## `businessContext` (type: `string`):

Short description of the product or support team.

## `replySignature` (type: `string`):

Optional signature appended to reply drafts.

## `includeReplyDraft` (type: `boolean`):

Generate a customer-facing response draft for each ticket.

## `includeFaqCandidates` (type: `boolean`):

Generate FAQ/knowledge-base candidate snippets when the ticket includes reusable guidance.

## Actor input object example

```json
{
  "tickets": [
    {
      "id": "T-1001",
      "customerName": "Jordan Lee",
      "subject": "Charged twice and still cannot access my account",
      "message": "I was charged twice yesterday and the login link still says my account is disabled. This is blocking my team. Please fix this today or refund us.",
      "channel": "email",
      "customerTier": "business"
    }
  ],
  "defaultLanguage": "English",
  "brandVoice": "calm, concise, and helpful",
  "businessContext": "SaaS support team handling billing, account access, onboarding, bugs, cancellations, and feature questions.",
  "replySignature": "Support Team",
  "includeReplyDraft": true,
  "includeFaqCandidates": true
}
```

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "tickets": [
        {
            "id": "T-1001",
            "customerName": "Jordan Lee",
            "subject": "Charged twice and still cannot access my account",
            "message": "I was charged twice yesterday and the login link still says my account is disabled. This is blocking my team. Please fix this today or refund us.",
            "channel": "email",
            "customerTier": "business"
        }
    ],
    "businessContext": "SaaS support team handling billing, account access, onboarding, bugs, cancellations, and feature questions.",
    "replySignature": "Support Team"
};

// Run the Actor and wait for it to finish
const run = await client.actor("jumpy_invoice/support-triage-intelligence").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "tickets": [{
            "id": "T-1001",
            "customerName": "Jordan Lee",
            "subject": "Charged twice and still cannot access my account",
            "message": "I was charged twice yesterday and the login link still says my account is disabled. This is blocking my team. Please fix this today or refund us.",
            "channel": "email",
            "customerTier": "business",
        }],
    "businessContext": "SaaS support team handling billing, account access, onboarding, bugs, cancellations, and feature questions.",
    "replySignature": "Support Team",
}

# Run the Actor and wait for it to finish
run = client.actor("jumpy_invoice/support-triage-intelligence").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "tickets": [
    {
      "id": "T-1001",
      "customerName": "Jordan Lee",
      "subject": "Charged twice and still cannot access my account",
      "message": "I was charged twice yesterday and the login link still says my account is disabled. This is blocking my team. Please fix this today or refund us.",
      "channel": "email",
      "customerTier": "business"
    }
  ],
  "businessContext": "SaaS support team handling billing, account access, onboarding, bugs, cancellations, and feature questions.",
  "replySignature": "Support Team"
}' |
apify call jumpy_invoice/support-triage-intelligence --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,jumpy_invoice/support-triage-intelligence"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/9bu7z5P5oviKBFa7a/builds/Ig3lxtF52sZw2b7Js/openapi.json