# Vendor performance review prompt: free ChatGPT template > Turn your purchase order log into a fair vendor review: on-time and short shipments from your records, your own changes set apart, and calm talking points. Source: https://learn.ynteractive.com/content/prompts/vendor-performance-review-prompt · Updated 2026-10-01 · Free from Stepthrough (https://learn.ynteractive.com) [SOPs and operations](https://learn.ynteractive.com/content/prompts#job-sops-and-operations) · [Operations](https://learn.ynteractive.com/content/prompts#industry-operations) · Works in ChatGPT, Claude, Gemini and Copilot Updated October 1, 2026 · By [Robert Breen](https://learn.ynteractive.com/content/about) Use this before a quarterly check-in with a supplier, or when you're deciding whether to keep one. Memory says "they're always late"; the log may say two late orders out of three, or one out of twenty. This prompt works from your own purchase order log, calculates simple measures, separates the vendor's misses from changes you made, and gives you talking points for the call. ## 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](https://learn.ynteractive.com/content/prompt-writing-101-role-context-task-format): Role, Context, Task and Format. Copy prompt ```text Role: You are an operations analyst at [BUSINESS] preparing a fair review of our vendors. Context: Below is our purchase order log for [PERIOD], with the header row. What we expect from vendors: [EXPECTATIONS]. Changes on our side that affected orders: [OUR SIDE]. Use only the rows; treat a blank as unknown, not as a miss. Task: For each vendor, count orders, on-time deliveries, late deliveries with days late, and short or wrong shipments, and average the reply days where recorded. Set apart misses caused by our changes. Then write three talking points per vendor: one thing that went well, the main issue with numbers, and one specific ask. Format: A short table per vendor with the row numbers behind each figure, then the talking points. Neutral, factual wording. No threats, penalties or "final warning" language. PO log: [PO LOG] ``` ## Fill in the blanks **`[BUSINESS]`** Your business name and what you do. **`[PERIOD]`** The months the log covers. **`[EXPECTATIONS]`** Your standards: ship on the promised date, full quantity, reply within a set time. **`[OUR SIDE]`** Orders you changed, rushed or paid late, so they aren't counted against the vendor. **`[PO LOG]`** One row per order with a row number, promised and delivered dates, quantities and reply days. ## Example, filled in **A made-up example** from the free lesson [Build an AI Vendor Follow-Up Agent in n8n](https://learn.ynteractive.com/content/ai-vendor-follow-up-agent-n8n). Ridgeline Supply Co. is the made-up warehouse business in the vendor follow-up agent lesson, which writes follow-ups for late or pending purchase orders. The operations manager pulled the quarter's PO log before calling each vendor. Copy example ```text Role: You are an operations analyst at Ridgeline Supply Co., a small warehouse and distribution business, preparing a fair review of our vendors. Context: Below is our purchase order log for July to September, with the header row. What we expect from vendors: ship on the promised date, ship the full quantity, and reply to a follow-up within 1 business day if an order is late or 2 if it's pending. Changes on our side that affected orders: we changed PO 4455 to Corrugo Box Supply two days before it shipped. Use only the rows; treat a blank as unknown, not as a miss. Task: For each vendor, count orders, on-time deliveries, late deliveries with days late, and short or wrong shipments, and average the reply days where recorded. Set apart misses caused by our changes. Then write three talking points per vendor: one thing that went well, the main issue with numbers, and one specific ask. Format: A short table per vendor with the row numbers behind each figure, then the talking points. Neutral, factual wording. No threats, penalties or "final warning" language. PO log: Row | PO | Vendor | Item | Promised | Delivered | Qty ordered | Qty received | Reply days 2 | 4410 | Tallpine Pallet Co. | Pallets | Jul 8 | Jul 8 | 200 | 200 | 3 | 4431 | Tallpine Pallet Co. | Pallets | Aug 5 | Aug 7 | 200 | 200 | 1 4 | 4471 | Tallpine Pallet Co. | Pallets | Sep 9 | Sep 14 | 150 | 150 | 2 5 | 4420 | Corrugo Box Supply | Boxes | Jul 15 | Jul 15 | 1000 | 1000 | 6 | 4455 | Corrugo Box Supply | Boxes | Aug 20 | Aug 23 | 1500 | 1500 | 1 7 | 4492 | Northwind Wrap | Stretch wrap | Sep 16 | Sep 16 | 60 | 48 | 1 ``` ## What a good answer looks like - Tallpine Pallet Co.: 3 orders, 1 on time, 2 late by 2 and 5 days (rows 2 to 4). - Corrugo's late PO 4455 set apart as our change, not their miss. - Northwind Wrap's PO 4492 counted as on time but 12 rolls short. - One specific ask per vendor, such as a ship-date confirmation from Tallpine two days before each delivery. ## 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](https://learn.ynteractive.com/content/chatgpt-reply-to-customer-emails): check every promise, name, date and number against what you gave it before anything goes out. - Recount the on-time and late figures from the log. With three orders, one late delivery is a third of the total, so be careful calling it a trend. - Compare reply days with your email; blanks mean nobody recorded them. - Share the numbers with the vendor before deciding anything. Their records may explain a gap. ## Why this prompt works Setting your own changes apart from the vendor's misses is what makes a review fair, and row numbers let the vendor see exactly which [purchase orders](https://learn.ynteractive.com/content/glossary/purchase-order) you mean. ## Practice it in the free lesson **[Build an AI Vendor Follow-Up Agent in n8n](https://learn.ynteractive.com/content/ai-vendor-follow-up-agent-n8n)**: Build an AI agent for Ridgeline Supply Co. that writes follow-up messages for late or pending purchase orders and saves them to Google Sheets — chat trigger, AI Agent, system prompt, model, memory, and the Sheets tool. You do every step yourself in a practice copy of n8n, and nothing touches your real accounts. [Start the free lesson](https://learn.ynteractive.com/modules/n8n-ai-agent-operations) Also useful: [Build an AI Maintenance and IT Request Form](https://learn.ynteractive.com/content/ai-maintenance-it-request-form-lovable-n8n) ## Terms used here [Purchase order](https://learn.ynteractive.com/content/glossary/purchase-order) · [Google Sheets (as an automation database)](https://learn.ynteractive.com/content/glossary/google-sheets) ## Related prompts - [Vendor late order follow-up prompt](https://learn.ynteractive.com/content/prompts/vendor-late-order-follow-up-prompt): Write a short, firm follow-up to a vendor about a late, short or unshipped purchase order: the PO, the problem, one question and… - [Vendor quote comparison prompt](https://learn.ynteractive.com/content/prompts/vendor-quote-comparison-prompt): Compare vendor quotes side by side on price, what's included, timing and warranty, with "Not in quote" for gaps and the… - [Vendor onboarding checklist prompt](https://learn.ynteractive.com/content/prompts/vendor-onboarding-checklist-prompt): Turn your purchasing rules into a vendor onboarding checklist with owners and due dates, plus the email telling the new vendor… [All free prompt templates](https://learn.ynteractive.com/content/prompts) · [AI glossary](https://learn.ynteractive.com/content/glossary)