Backlog & Aging Work-Order Monitor

The problem this kills

Open work orders pile up quietly. One is waiting on a backordered part, another is waiting on a customer who never called back, a third never got scheduled at all - and three weeks later a customer is furious because their job "fell through the cracks." It didn't fall anywhere. It just sat in a list nobody was reading top to bottom, mixed in with 200 other jobs, with no easy way to see which ones had gone stale and whose fault the delay was.

Most teams "monitor" this by scrolling a giant export every Monday and eyeballing dates. That misses things, it can't tell "waiting on us" from "waiting on the customer," and it has no record of who decided to do what about each stale job.

What you'll build

A small, private web app for your dispatch / service team that:

• Takes your open work orders (from a CSV export or a Google Sheet) - status, age, and waiting-reason.
• Sorts every open job into aging buckets (e.g. 0-7 days, 8-14, 15-30, 30+) using thresholds you set per status, because "5 days unscheduled" and "5 days waiting on a part" are not the same kind of late.
• Flags the stale ones and clearly separates waiting on us (unscheduled, waiting parts) from waiting on the customer - so accountability is obvious at a glance.
• Sends each flagged job to a manager for a decision: schedule, escalate, or close - with a one-line reason.
• Only after a human approves does it record the action, then hands it off and lets you export the aging report and the approved actions as CSV to drop back into your system.

What's inside the Implementation Plan

• It starts by interviewing you about your business. Before building anything, the plan has the AI agent ask you about your real work-order statuses, your waiting-reasons, your field and ID naming, your typical and peak backlog size, and your aging thresholds - then it tailors the data model and rules to you. No generic template that assumes statuses you don't use.
• A copy-paste prompt for every step, in order, so you never have to know what to type.
• A clean data model for work orders, aging buckets, and the approval/action log.
• The full manager approval gate, audit trail, login, and per-org data isolation wired in from the start.
• Duplicate protection so the same work order can't be counted or actioned twice.
• A guaranteed "No API yet?" fallback - run the whole thing off a sheet and export CSV, today, with zero integrations.

The governance it includes (this is the point)

This isn't a throwaway script. The plan builds in the controls that make a tool safe to actually run your backlog on:

• Login so only your team can open it.
• Row-level security so each organization only ever sees its own work orders.
• A complete audit trail - who flagged what, who approved which action, and when.
• A hard human-in-the-loop gate - the tool drafts a recommended next action, but nothing is recorded as a decision until a manager reviews and approves it.
• Duplicate guards keyed on the work-order ID so re-importing the same export never double-counts.

Who it's for

Dispatchers, service managers, and coordinators who own a backlog of open jobs and are tired of finding out about stale work orders from an angry customer instead of from a report. If you can export your open work orders to a spreadsheet, you can build this.

You've got this - paste the first prompt and let the agent interview you.