Return Reason Analytics

The problem this kills

Returns are eating your margin, and nobody can say exactly why. The reasons live in a free-text field full of "to small", "didnt fit", "DEFECTIVE!!!", and "wrong color" - the same problem typed fifteen different ways. Every month someone hand-rolls a spreadsheet, eyeballs the worst SKUs, and emails a chart that's out of date the moment it lands.

Meanwhile the product team doesn't know which vendor keeps shipping defects, the category manager can't see that one channel returns twice as often as the rest, and a slow rise in return rate goes unnoticed until it's a crisis. The signal is in your data. It's just buried under typos and copy-paste.

What you'll build

A small internal web app that does the boring, careful work for you:

• Imports your returns history from a CSV or Google Sheet - no integration required.
• Normalizes messy free-text reasons into a clean, consistent code set (defect, wrong item, sizing, damaged in transit, changed mind, and so on) so the same problem always counts as the same problem.
• Aggregates and ranks root causes by SKU, category, vendor, and channel - so the worst offenders rise to the top instead of hiding in the long tail.
• Flags rising return rates so a creeping problem gets caught early, not after the quarter closes.
• Generates a monthly insight snapshot that a manager reviews and approves before it goes anywhere.
• Emails the approved report to your product and vendor teams through Resend, with a clean CSV attached.

What's inside the Implementation Plan

The plan is a single file you paste into an AI coding agent (Claude Code). It builds the whole tool with you, step by step, in plain language.

It opens by interviewing you about your business - your current returns process, the systems and spreadsheets you use, the exact columns and codes in your data, your typical and peak volumes, and your messy edge cases. It reads back a short tailored spec, waits for your thumbs-up, and only then starts building. You get a tool shaped around how you actually handle returns, not a generic template you have to bend to fit.

Inside you'll find:

• The exact discovery questions the agent asks before writing any code.
• A data model tuned to your real reason codes, SKU naming, and vendor mapping.
• The free-text normalization rules that turn "to small" and "didnt fit" into one clean sizing code.
• The ranking and rising-rate logic that surfaces the true worst offenders.
• The manager approval gate, the audit trail, and the monthly email + CSV export.
• A copy-paste prompt at the end of every step, plus a no-API fallback so you can ship today.

The governance it includes (this is the point)

This isn't a throwaway script - it's a tool your team can trust with real numbers:

• Login so only your team can open it.
• Row-level security so people only ever see their own organization's data.
• A complete audit trail - who imported what, who edited a reason mapping, who approved the monthly snapshot, and when.
• A hard human-in-the-loop approval gate - the tool drafts the monthly insight report, a manager reviews and approves it, and only then is it distributed.
• Duplicate guards so the same return event can't be counted twice and the same month can't be sent twice.

Who it's for

• Quality teams who need to prove which vendor or SKU is driving defects.
• Category managers who want returns broken down by category and channel.
• Ops leadership who want one trustworthy monthly number instead of five conflicting spreadsheets.

You don't need to know how to code. You need to know your returns process - the plan handles the rest.

You've got this. Paste the first prompt and let the interview tailor the tool to your business.