The Ticket Pipeline

Description

GOAL
Build a workflow that starts automatically on every newly incoming IT support ticket: categorization, a knowledge base search, deriving a solution proposal, and automatically assigning the ticket to the responsible team.

Adapt the structure to the concepts of your automation tool (for example nodes, steps, zaps or agent actions). While doing so, preserve the trigger logic, the sequence and the data flow.

TRIGGER
Type: webhook or native integration with your ticket system (Zendesk, Freshdesk, Jira Service Management or comparable).
Input: ticket ID, subject, description.

STEPS
1. AI step: categorization. Use exactly the Ticket Categorization working prompt (see the Working Prompts section). Output: JSON with category, urgency (1 to 5) and reasoning.
2. Search the knowledge base: using the category and the core terms from the description, find similar, already resolved tickets and matching solution articles, including links to the matches.
3. AI step: solution proposal. Use exactly the Solution Proposal working prompt (see the Working Prompts section) with the matches found as input. Output: formatted markdown comment.
4. Add the comment: save the solution proposal as an internal comment on the ticket, not as a reply to the customer.
5. Assignment: assign the ticket automatically via the category to team mapping (hardware, software, network, access). Optionally derive the priority from the urgency.

PROMPTS
Take over both working prompts from the section of the same name unchanged. Do not alter the placeholders they contain, and map them as described in the data flow.

DATA FLOW
Trigger to step 1: ticket ID, subject, description.
Step 1 to steps 2, 3 and 5: category; urgency additionally for an optional priority.
Step 2 to step 3: knowledge base matches found.
Step 3 to step 4: formatted comment.

ERROR HANDLING
No knowledge base matches: do not abort the run. In this case, the Solution Proposal working prompt provides general best practices for the identified category.
No valid JSON from step 1: retry once, then assign the ticket to the standard triage team and log the error.
Category not clearly identifiable: choose the most likely category and state the uncertainty in the reasoning.
API error while commenting or assigning: log the error and notify the workflow owner.

PLACEHOLDER CONVENTION
All placeholders in square brackets inside the two working prompts are fully mapped dynamically, as described in the data flow. There are no placeholders that require manual configuration in the prompts themselves. Only the system access credentials and the category to team mapping are configured manually.

SELF CHECK BEFORE COMPLETION
Check, before you report the workflow as finished:
1. Are all five steps connected correctly and in the right order?
2. Are both working prompts inserted in full and unchanged, and are all placeholders mapped?
3. Is the JSON from step 1 parsed correctly, and is the comment saved as an internal comment, not as a reply to the customer?
4. Are all points listed that require manual configuration: ticket system access, knowledge base access, the category to team mapping, and LLM access?

Working prompts

You are an IT support assistant who analyzes and categorizes incoming support tickets.

Analyze the following support ticket:

Ticket ID: [TICKET_ID]
Subject: [TICKET_SUBJECT]
Description: [TICKET_DESCRIPTION]

Your task:
1. Identify the main problem in the ticket description.
2. Assign the problem to EXACTLY ONE of the following categories:
- Hardware (physical devices, printers, monitors, keyboards and similar)
- Software (applications, programs, licenses, updates and similar)
- Network (WiFi, VPN, connection issues, internet outages and similar)
- Access (login problems, passwords, permissions, account management and similar)
3. Rate the urgency on a scale from 1 (low) to 5 (critical).

Respond in the following JSON format:
{
  "category": "[Category]",
  "urgency": [1-5],
  "reasoning": "[Brief reasoning in one to two sentences]"
}

You are an IT support expert who creates solution proposals for support tickets.

Current ticket:
- Category: [CATEGORY]
- Subject: [TICKET_SUBJECT]
- Description: [TICKET_DESCRIPTION]

Knowledge base articles and similar tickets found:
[KNOWLEDGE_BASE_RESULTS]

Your task:
Create a structured comment for the support team with the following information:
1. Summary of the problem (one to two sentences)
2. The three most likely solution suggestions based on the articles found
3. Links to the relevant knowledge base articles
4. Recommended next steps for the support team

Format the comment professionally and practically. Use markdown for better readability.

Important: if no matching articles were found, provide general best practices for the [CATEGORY] category.

JSON export