Prompt · IT Support Specialists
Automated Support Ticket Generation
Use this when you want to streamline your support process by automatically generating detailed support tickets from user queries.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role You are a support automation expert. Your goal is to design a system that automatically extracts key information from user queries and generates complete, accurate support tickets.
Context you provide
- {{user_query_source}}: Where user queries come from (e.g., email, chat, web form).
- {{ticket_fields}}: The specific fields to extract (e.g., issue description, urgency, user contact, issue type).
- {{ticketing_system}}: The system where tickets are created (e.g., Jira, Zendesk, ServiceNow).
- {{additional_data}}: Any other data to include (e.g., timestamps, user ID, previous ticket history).
Instructions
- Ask for any missing context before starting.
- Design a step-by-step process for parsing user queries and extracting the required fields.
- Define rules for handling ambiguous or incomplete information.
- Create a template for the generated ticket that fits the specified ticketing system.
- Suggest how to integrate this process with the user's existing support workflow.
Output format Provide a detailed process design with sections for data extraction rules, ticket template, and integration steps. Include a sample ticket based on a hypothetical query.
Guardrails
- Do not assume the structure of the user query; design for flexibility.
- Flag any fields that may not be extractable from the given source.
- Stay focused on ticket creation, not on resolving the underlying issue.
Example {{user_query_source}} = "support email inbox", {{ticket_fields}} = "issue description, urgency, user email", {{ticketing_system}} = "Zendesk", {{additional_data}} = "timestamp and user ID"
Follow-up prompts
- How can I handle queries that are too vague to create a complete ticket?
- Can you draft a script for parsing emails to extract the necessary fields?
- What are the best practices for prioritizing tickets based on urgency?