Supplier Scorecard & OTD / Quality Tracker

The problem this kills

Your quarterly supplier business review is on the calendar, and you are walking in with a story instead of a number. "They've been late a lot lately." "Quality felt worse this quarter." "I think we had a few rejects." The supplier nods, promises to do better, and nothing changes — because you never put a hard, repeatable score in front of them.

Meanwhile the data already exists. Every PO has a promised date and an actual receipt date. Every receiving discrepancy and reject is logged somewhere. But it lives across exports and spreadsheets, nobody has time to reconcile it line by line, and so the metrics never make it into the review. You end up rating suppliers on memory and vibes, the loud ones get the benefit of the doubt, and the quietly-failing ones slide.

This is exactly the kind of rules-based, high-stakes scoring that a small internal tool does better than a spreadsheet — define your on-time tolerance and your weights once, feed it the data, and get the same defensible score every period. And you do not need to be a developer to build it.

What you'll build

A simple internal web tool for supplier performance. You import two files — your PO delivery facts (promised date vs. actual receipt date, by PO line) and your receiving discrepancy / reject records — and optionally a third for price and responsiveness. The tool computes, per supplier per period: on-time delivery % against your early/late tolerance windows, defect / reject rate, and a weighted overall score using the weights you set. It trends each supplier over time so you can see who is improving and who is sliding.

AI drafts the period's scorecard and a letter-grade rating, and flags the messy cases — partial deliveries, missing promised dates, suppliers with too little data to score fairly. The procurement owner reviews the whole list on one screen, adjusts anything that looks wrong, and clicks Approve. Only then does the tool produce a shareable scorecard PDF, a supplier-review packet, a CSV export, and a scheduled summary email. Ratings are confirmed by a person — never auto-published to the supplier.

What's inside the Implementation Plan

The plan is a single file you paste into an AI coding agent. It opens by interviewing you about your business — how you run supplier reviews today, what systems hold your PO and receiving data, the exact column names and supplier/SKU codes in your exports, your on-time tolerance windows, your scoring weights, your minimum-data rules, and your nastiest edge cases — and then tailors the data model, the scoring engine, and every later step to your answers. This is a build shaped around how you rate suppliers, not a generic template.

From there it walks the agent through the database schema, the two-or-three CSV imports with their duplicate guards, the OTD / quality / weighted-score engine, the per-supplier trend view, the owner's review-and-approve screen, and the export of the scorecard PDF, the review packet, and the CSV. Every step ends with a ready-to-copy prompt. Because the whole thing runs on CSV in and a clean PDF + CSV out, you can build and use it this weekend even with no integration to your ERP — and feed it straight from your receiving and OS&D tools later.

The governance it includes (this is the point)

A supplier score becomes a contractual conversation, so it is built like it matters: login so only your procurement / supplier-quality team can use it, row-level security so you only ever see your own organization's suppliers, and a complete audit trail of every import, edit, approval, and export — who did what, and when. Nothing goes to a supplier automatically: the scorecard is a draft until the procurement owner approves it, and approval is the hard human-in-the-loop gate before any rating is finalized or shared. Duplicate guards mean the same delivery can't be counted twice (deduped on the PO line) and the same supplier can't get two scorecards for one period (deduped on supplier + period).

Who it's for

Procurement leads and supplier-quality engineers (SQEs) who run supplier business reviews and are tired of arguing from anecdotes. If you can explain how you decide whether a delivery was on time and how you'd weight delivery against quality, you can build this.

You've got this — open the plan, paste the first prompt, and let it interview you about how you rate your suppliers.