Maintenance request triage prompt: free ChatGPT template
Updated · By Robert Breen
Use this when broken-thing requests arrive faster than you can read them: a door that won't open, a dead scanner, a light out, a login that fails. You give the AI your priority rules and your teams, paste the requests, and get back a sorted table. Every priority comes with the exact words that drove it, so you can overrule a bad call in seconds.
Want it to happen on its own? The free maintenance and IT request form lesson builds a form and an n8n agent that applies the same rules to each request as it arrives.
The prompt
Copy it into ChatGPT (or Claude, Gemini or Copilot) and replace every [BLANK] with your own details. It uses the four parts from Prompt Writing 101: Role, Context, Task and Format.
Role: You are the maintenance and IT request coordinator for [BUSINESS]. Context: Priority rules: [PRIORITY RULES]. Teams: [TEAMS]. Judge each request only by what it says. If a request is too vague to judge, mark it "Needs info" and say what to ask, instead of guessing. Anything that could hurt someone is never the lowest priority. Task: For each request, give a priority and one team, a one-line reason that quotes the words in the request that drove the choice, and a short confirmation line for the person who sent it. Don't promise a fix time. Format: A table with the columns Request, Location, Priority, Team, Reason, Confirmation, with the most urgent rows first. After the table, one line counting requests by priority. Here are today's requests, one per line: [REQUESTS]
Fill in the blanks
[BUSINESS]- Your business name and what kind of site it is (warehouse, shop, office).
[PRIORITY RULES]- Your levels and what puts a request in each one. Specific rules ("stops shipping or receiving") beat vague ones ("important").
[TEAMS]- The teams or people who fix things, each with what they cover.
[REQUESTS]- The requests as people wrote them, with location. Don't clean them up; the original words are what the reasons quote.
Example, filled in
A made-up example from the free lesson Build an AI Maintenance and IT Request Form. Ridgeline Supply Co. is the made-up warehouse in the maintenance and IT request form lesson. The rules and teams below are the ones its agent uses; the requests are a made-up Monday morning.
Role: You are the maintenance and IT request coordinator for Ridgeline Supply Co., a small warehouse business. Context: Priority rules: Urgent (safety risk, or it stops shipping or receiving), This week, or Backlog. Teams: Facilities, IT, or Equipment. Judge each request only by what it says. If a request is too vague to judge, mark it "Needs info" and say what to ask, instead of guessing. Anything that could hurt someone is never the lowest priority. Task: For each request, give a priority and one team, a one-line reason that quotes the words in the request that drove the choice, and a short confirmation line for the person who sent it. Don't promise a fix time. Format: A table with the columns Request, Location, Priority, Team, Reason, Confirmation, with the most urgent rows first. After the table, one line counting requests by priority. Here are today's requests, one per line: Dock door 3 will not open. Two trucks are waiting. (Dock 3) Scanner 4 won't hold a charge, swapping it every hour. (Dock 1) Light out over aisle 12, pretty dark on second shift. (Aisle 12) Can't log in to the WMS on the front office PC. (Office) Breakroom microwave smells weird. (Breakroom) Something's wrong with the forklift. (Green lane)
What a good answer looks like
- Dock door 3 first: Urgent, Facilities, quoting "Two trucks are waiting."
- The dark aisle kept off Backlog, since poor light on a shift can be a safety risk. Confirm that call yourself.
- The forklift marked "Needs info," with a question like "What is it doing, and is it parked and out of use?"
- Confirmations that say what happens next without promising a time, such as "Facilities has it as Urgent."
How to check it before you use it
An AI draft can sound right and still say something you never told it. Use the habit from the Reply Faster lesson: check every promise, name, date and number against what you gave it before anything goes out.
- Read the Urgent and Backlog rows yourself. Those are the two calls that hurt most when they're wrong.
- Check that each quoted reason is really in the request. A reason the requester never wrote means the model guessed.
- Look for a safety risk the model ranked low. Your rules say it can't happen; make sure it didn't.
- Make sure no confirmation promises a fix by a time you didn't give.
Practice it in the free lesson
Build an AI Maintenance and IT Request Form: Build an internal maintenance and IT request form in Lovable for Ridgeline Supply Co. and connect it to n8n — the AI agent sets the priority, assigns a team, saves the request to Google Sheets and emails a confirmation. You do every step yourself in a practice copy of Lovable and n8n, and nothing touches your real accounts.
Also useful: Build an AI Vendor Follow-Up Agent in n8n
Terms used here
Related prompts
- Incident report prompt: Draft an internal incident or near-miss report from your notes and witness statements: facts in order, who said what, gaps…
- Emergency service request triage prompt: Sort a batch of plumbing service requests by your own priority rules, flag unclear ones to call, and draft first replies using…
- Shift handoff notes prompt: Turn end-of-shift scribbles into a clear handoff for the next shift: what to do first, work in progress, promises to customers…
- Email to task list prompt: Turn a long email thread into a to-do list: every request, promise and unanswered question, who asked and when, what is overdue…