--- title: How do I keep a plate remnant inventory and match new cut lists to drops before buying plate, with AI? | AEC Agents url: https://aecagents.si/use-cases/plate-remnant-inventory-match-cut-list description: Most shops have a rack of usable plate drops that nobody can find on paper, so new jobs get nested on fresh sheets while good remnants sit until they turn into scrap. Keep one table of every full sheet and every drop worth saving (tag number, grade, thickness, size, heat number, parent sheet, rack location, status), and have Copilot in Excel or Gemini in Google Sheets, or a short script Claude or ChatGPT writes for you, match each new cut list against it by grade and thickness and list the drops large enough to try first. Claude or ChatGPT can also read handwritten drop tags and cut sheets into the table. The nesting itself, and whether a drop's heat number and condition are acceptable for the job, stay with the shop. last_modified: 2026-11-11 source: AEC Agents (free, open workflows; not engineering advice) --- [AI assists](https://aecagents.si/use-cases/plate-remnant-inventory-match-cut-list#honesty-labels)Workflow guide · not independently tested # How do I keep a plate remnant inventory and match new cut lists to drops before buying plate, with AI? Most shops have a rack of usable plate drops that nobody can find on paper, so new jobs get nested on fresh sheets while good remnants sit until they turn into scrap. Keep one table of every full sheet and every drop worth saving (tag number, grade, thickness, size, heat number, parent sheet, rack location, status), and have Copilot in Excel or Gemini in Google Sheets, or a short script Claude or ChatGPT writes for you, match each new cut list against it by grade and thickness and list the drops large enough to try first. Claude or ChatGPT can also read handwritten drop tags and cut sheets into the table. The nesting itself, and whether a drop's heat number and condition are acceptable for the job, stay with the shop. [Fabricator](https://aecagents.si/roles/fabricator) · Fabrication · Claude · ChatGPT · Microsoft Excel · Microsoft Copilot · Google Sheets Content updated 11 November 2026 · Tool links listed below; vendor features and pricing change, so confirm with the vendor ## Short answer Use Copilot in Excel or Gemini in Google Sheets, plus Claude or ChatGPT: Copilot or Gemini (or a short script Claude or ChatGPT writes) matches each part on a new plate cut list to available drops of the same grade and thickness that are big enough after your kerf and edge allowance, smallest first, and totals what still has to be bought; Claude or ChatGPT reads handwritten drop tags and cut sheets into the stock table. Most shops have a rack of usable plate drops that nobody can find on paper, so new jobs get nested on fresh sheets while good remnants sit until they turn into scrap. Keep one table of every full sheet and every drop worth saving (tag number, grade, thickness, size, heat number, parent sheet, rack location, status), and have Copilot in Excel or Gemini in Google Sheets, or a short script Claude or ChatGPT writes for you, match each new cut list against it by grade and thickness and list the drops large enough to try first. Claude or ChatGPT can also read handwritten drop tags and cut sheets into the table. The nesting itself, and whether a drop's heat number and condition are acceptable for the job, stay with the shop. A person still checks: drop sizes and condition on the rack, grade and heat traceability against the job's requirements, and the actual nest, with the programmer and quality staff. ## AI tie-in **Tool:** Copilot in Excel or Gemini in Google Sheets, plus Claude or ChatGPT Copilot or Gemini (or a short script Claude or ChatGPT writes) matches each part on a new plate cut list to available drops of the same grade and thickness that are big enough after your kerf and edge allowance, smallest first, and totals what still has to be bought; Claude or ChatGPT reads handwritten drop tags and cut sheets into the stock table. ### Prompt 1 ``` Read these photos of plate drop tags [upload]. Build a table with one row per tag: tag number, grade, thickness, width, length, heat number, parent tag and rack location, copying every value exactly as written. Write UNREADABLE for anything you cannot read and NOT SHOWN for anything missing. Do not convert units or fill gaps. ``` ### Prompt 2 ``` Here are the headers and a few sample rows of my Stock tab [paste] and my Cut List tab [paste]. Settings!B1 is my kerf plus edge allowance. Write Excel formulas (or a step-by-step Copilot plan) that list, for each part, up to three available rectangular drops of the same grade and thickness that fit the part plus the allowance in either orientation, smallest area first, with tag, location and heat number, and mark parts with no match as BUY. Do not assume grade substitutions or judge material suitability. ``` **Human check:** Drop sizes and condition on the rack, grade and heat traceability against the job's requirements, and the actual nest, with the programmer and quality staff. ## The problem Keep a plate remnant inventory and match new cut lists to drops before buying plate, with AI. This is a common, time-consuming task for a fabricator. ## What this workflow does Most shops have a rack of usable plate drops that nobody can find on paper, so new jobs get nested on fresh sheets while good remnants sit until they turn into scrap. Keep one table of every full sheet and every drop worth saving (tag number, grade, thickness, size, heat number, parent sheet, rack location, status), and have Copilot in Excel or Gemini in Google Sheets, or a short script Claude or ChatGPT writes for you, match each new cut list against it by grade and thickness and list the drops large enough to try first. Claude or ChatGPT can also read handwritten drop tags and cut sheets into the table. The nesting itself, and whether a drop's heat number and condition are acceptable for the job, stay with the shop. **How it works:** AI drafts or analyzes. A person operates the tools, checks the work, and takes action. **Your checkpoint:** The sheet only finds drops that are big enough on paper. It does not nest parts, check flatness, damage or edge condition, or decide whether a drop's grade and heat traceability satisfy the job's requirements. The nest, material acceptance and traceability records stay with the shop's programmer and quality staff. ## Before you start - Access to the named tool; confirm license, version and cost with the vendor. - A small, non-confidential sample to try the workflow on first. - A qualified person to review the output before it is used. ### Tools and access - [Claude (Anthropic)](https://www.anthropic.com/claude) - [ChatGPT](https://chatgpt.com/) - [Microsoft Excel](https://www.microsoft.com/microsoft-365/excel) - [Microsoft Copilot](https://www.microsoft.com/microsoft-365/copilot) - [Google Sheets](https://workspace.google.com/products/sheets/) ## Follow the steps 1. Set your keep rule first: the smallest drop width and length (or area) worth tagging and racking for each thickness range. Below that, it goes to scrap. You set the rule; the AI does not. 2. Keep a Stock tab, one row per piece: tag number, grade, thickness, width, length, shape note (rectangle or irregular), heat number, parent tag (the sheet or drop it was cut from), rack location, status (available, reserved, used, scrapped) and the date it was tagged. 3. When a sheet is cut, add a row for each drop you keep with the parent tag and the same heat number, and mark the parent used. If tags or cut sheets are handwritten, have Claude or ChatGPT read photos of them into those columns, copying values exactly and writing UNREADABLE instead of guessing. 4. For each new job, paste the plate part list (part mark, grade, thickness, width, length, quantity) into a Cut List tab. 5. Have Copilot in Excel or Gemini in Google Sheets, or a script the AI writes, list for each part the available drops of the same grade and thickness whose width and length both exceed the part plus your kerf and edge allowance, smallest suitable drop first, and total what is left to buy as full sheets. 6. Reserve the drops you actually nest on, update the statuses after cutting, and do a rack count against the Stock tab once a month. ## Try a small example Replace the bracketed fields with your own project details. No tested sample run is published for this workflow yet. ### Sample input ``` Fill in the bracketed [fields] in the text below with your project data. ``` ### Starter prompt ``` Here are the headers and a few sample rows of my Stock tab [paste: tag, grade, thickness, width, length, shape, heat number, parent tag, location, status] and my Cut List tab [paste: part mark, grade, thickness, width, length, quantity]. Settings!B1 is my kerf plus edge allowance in inches. Write Excel formulas (or a step-by-step Copilot plan) that, for each part, list up to three available rectangular drops with the same grade and thickness whose width and length both exceed the part dimensions plus the allowance in either orientation, smallest area first, and show the tag, location and heat number. Mark parts with no matching drop as BUY. Use only my data; do not assume grade substitutions, do not treat irregular drops as rectangles and do not judge material suitability. ``` ### Expected output ``` Not published yet. Treat any output as a draft and check it against the source documents. ``` ## Check the result - Every value, citation or quantity traces back to a source document. - Missing information is marked as missing, not filled in. ## Limits and recovery - The sheet only finds drops that are big enough on paper. It does not nest parts, check flatness, damage or edge condition, or decide whether a drop's grade and heat traceability satisfy the job's requirements. The nest, material acceptance and traceability records stay with the shop's programmer and quality staff. - Check your organization’s data policy before sharing project files with third-party tools. **Stop or switch when:** The source cannot be verified, permissions are missing, or the result contains unsupported facts. ## Frequently asked questions How does AI help with this? Copilot in Excel or Gemini in Google Sheets, plus Claude or ChatGPT: Copilot or Gemini (or a short script Claude or ChatGPT writes) matches each part on a new plate cut list to available drops of the same grade and thickness that are big enough after your kerf and edge allowance, smallest first, and totals what still has to be bought; Claude or ChatGPT reads handwritten drop tags and cut sheets into the stock table. A person still checks: Drop sizes and condition on the rack, grade and heat traceability against the job's requirements, and the actual nest, with the programmer and quality staff. How do I how do I keep a plate remnant inventory and match new cut lists to drops before buying plate, with AI?? Set your keep rule first: the smallest drop width and length (or area) worth tagging and racking for each thickness range. Below that, it goes to scrap. You set the rule; the AI does not. Keep a Stock tab, one row per piece: tag number, grade, thickness, width, length, shape note (rectangle or irregular), heat number, parent tag (the sheet or drop it was cut from), rack location, status (available, reserved, used, scrapped) and the date it was tagged. When a sheet is cut, add a row for each drop you keep with the parent tag and the same heat number, and mark the parent used. If tags or cut sheets are handwritten, have Claude or ChatGPT read photos of them into those columns, copying values exactly and writing UNREADABLE instead of guessing. The full step list is above. Does this use an AI agent or regular software? It is labeled AI assists: AI drafts or analyzes. A person operates the tools, checks the work, and takes action. What tools do I need? Claude, ChatGPT, Microsoft Excel, Microsoft Copilot, Google Sheets. Confirm license, version and cost with the vendor, and try it on a small non-confidential sample first. Has this workflow been tested? Workflow guide · not independently tested. Written from vendor documentation and practitioner use. Labels apply to the steps described here, not every feature of a product. Links were checked when the page was written. ## Where to go next - [How do I answer shop questions from drawings and specs with AI document search?](https://aecagents.si/use-cases/fabrication-shop-docs) - [How do I go from design model to shop drawings and CNC data in detailing software?](https://aecagents.si/use-cases/steel-detailing-model) - [How do I turn mill test reports into a material heat number traceability log with AI?](https://aecagents.si/use-cases/mtr-heat-number-traceability-log) - [All Fabricator workflows](https://aecagents.si/roles/fabricator) - [All Schedules, submittals and project controls workflows](https://aecagents.si/tasks/project-controls) ## Evidence and maintenance Written from vendor documentation and practitioner use. Labels apply to the steps described here, not every feature of a product. Links were checked when the page was written. - [Claude (Anthropic) (vendor site)](https://www.anthropic.com/claude) - [ChatGPT (vendor site)](https://chatgpt.com/) - [Microsoft Excel (vendor site)](https://www.microsoft.com/microsoft-365/excel) - [Microsoft Copilot (vendor site)](https://www.microsoft.com/microsoft-365/copilot) - [Google Sheets (vendor site)](https://workspace.google.com/products/sheets/) ## Put it to work Start with a small sample and keep the original record open while you verify the result. ## Know what does the work. Agent executes : An AI agent calls connected tools to carry out bounded actions. You set permissions and review the result. AI assists : AI drafts or analyzes. A person operates the tools, checks the work, and takes action. Conventional automation : Rules or specialist software perform the task. No AI agent is required.