--- title: How do I check a door hardware submittal against the door schedule and hardware sets with AI? | AEC Agents url: https://aecagents.si/use-cases/door-hardware-submittal-vs-door-schedule description: A door hardware submittal can run to hundreds of pages, and the review usually comes down to tedious matching: does every opening on the door schedule appear in the submitted hardware schedule, with the specified set, the right quantity of each item, the specified finish and fire-rated product where the opening is rated. Resubmittals often come from mismatches nobody caught until the third round. Have Claude or ChatGPT read the submitted hardware schedule and your door schedule and hardware sets into tables, and have Copilot in Excel or Gemini in Google Sheets match them opening by opening and flag every difference for your review. Whether a substitution is acceptable, and whether an opening meets egress, accessibility or fire requirements, stays with the architect and the hardware consultant. last_modified: 2026-11-11 source: AEC Agents (free, open workflows; not engineering advice) --- [AI assists](https://aecagents.si/use-cases/door-hardware-submittal-vs-door-schedule#honesty-labels)Workflow guide · not independently tested # How do I check a door hardware submittal against the door schedule and hardware sets with AI? A door hardware submittal can run to hundreds of pages, and the review usually comes down to tedious matching: does every opening on the door schedule appear in the submitted hardware schedule, with the specified set, the right quantity of each item, the specified finish and fire-rated product where the opening is rated. Resubmittals often come from mismatches nobody caught until the third round. Have Claude or ChatGPT read the submitted hardware schedule and your door schedule and hardware sets into tables, and have Copilot in Excel or Gemini in Google Sheets match them opening by opening and flag every difference for your review. Whether a substitution is acceptable, and whether an opening meets egress, accessibility or fire requirements, stays with the architect and the hardware consultant. [Architect](https://aecagents.si/roles/architect) · Architecture · 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 Claude or ChatGPT, then Copilot in Excel or Gemini in Google Sheets: Claude or ChatGPT reads the submitted hardware schedule into one row per item per opening; Copilot or Gemini matches it to your door schedule and specified sets and flags missing openings, item, quantity, function and finish differences and possible substitutions. A door hardware submittal can run to hundreds of pages, and the review usually comes down to tedious matching: does every opening on the door schedule appear in the submitted hardware schedule, with the specified set, the right quantity of each item, the specified finish and fire-rated product where the opening is rated. Resubmittals often come from mismatches nobody caught until the third round. Have Claude or ChatGPT read the submitted hardware schedule and your door schedule and hardware sets into tables, and have Copilot in Excel or Gemini in Google Sheets match them opening by opening and flag every difference for your review. Whether a substitution is acceptable, and whether an opening meets egress, accessibility or fire requirements, stays with the architect and the hardware consultant. A person still checks: every flag against the submittal pages; substitutions, fire rating, egress and accessibility questions stay with the architect and hardware consultant. ## AI tie-in **Tool:** Claude or ChatGPT, then Copilot in Excel or Gemini in Google Sheets Claude or ChatGPT reads the submitted hardware schedule into one row per item per opening; Copilot or Gemini matches it to your door schedule and specified sets and flags missing openings, item, quantity, function and finish differences and possible substitutions. ### Prompt 1 ``` Read this door hardware submittal [upload]. Build a table with one row per item per opening: opening number, set as submitted, item, quantity, manufacturer and model, function, finish code and any listing reference shown. Copy entries exactly and write NOT SHOWN instead of guessing. ``` ### Prompt 2 ``` Here are the headers and a few sample rows of my DoorSchedule, Sets and Submitted tabs [paste]. Write Excel formulas (or a step-by-step Copilot plan) that flag missing or extra openings and items, quantity, function and finish differences, rated openings with no listing reference and non-specified products, summarized by opening. Use only my data and don't judge equivalence or compliance. ``` **Human check:** Every flag against the submittal pages; substitutions, fire rating, egress and accessibility questions stay with the architect and hardware consultant. ## The problem Check a door hardware submittal against the door schedule and hardware sets with AI. This is a common, time-consuming task for a architect. ## What this workflow does A door hardware submittal can run to hundreds of pages, and the review usually comes down to tedious matching: does every opening on the door schedule appear in the submitted hardware schedule, with the specified set, the right quantity of each item, the specified finish and fire-rated product where the opening is rated. Resubmittals often come from mismatches nobody caught until the third round. Have Claude or ChatGPT read the submitted hardware schedule and your door schedule and hardware sets into tables, and have Copilot in Excel or Gemini in Google Sheets match them opening by opening and flag every difference for your review. Whether a substitution is acceptable, and whether an opening meets egress, accessibility or fire requirements, stays with the architect and the hardware consultant. **How it works:** AI drafts or analyzes. A person operates the tools, checks the work, and takes action. **Your checkpoint:** The comparison only checks the submittal against the schedule and sets you entered, so an error in your own door schedule carries through. A flag is something to look at, not a rejection, and a clean opening hasn't been checked for egress, accessibility, fire rating or security requirements. Review actions, substitutions and code questions stay with the architect and the hardware consultant. ## 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. Export your door schedule from the model or drawings to a spreadsheet (opening number, door and frame type, fire rating, hardware set) and put the hardware sets from your specification into a Sets tab, one item per row with quantity, function and finish. 2. Have Claude or ChatGPT read the submitted hardware schedule into a Submitted tab with one row per item per opening: opening number, set number as submitted, item, quantity, manufacturer and model, function, finish code and any rated-product listing reference shown. It copies entries exactly and writes NOT SHOWN instead of guessing. 3. Have it list, on a separate tab, every opening in the submittal that isn't on your door schedule and every scheduled opening missing from the submittal. 4. Have Copilot in Excel or Gemini in Google Sheets compare each opening's submitted items with the specified set: missing or extra items, quantity differences, finish differences, a different function, and rated openings with no listing reference shown for the item. 5. Flag items where the manufacturer or model differs from the specified product as possible substitutions, without judging whether they're equivalent. 6. Use the flagged list as the backbone of your review comments, checking each against the submittal pages, and keep the tab so the resubmittal can be compared the same way. ## 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 DoorSchedule tab [paste: opening, door type, frame type, fire rating, hardware set], my Sets tab from my specification [paste: set, item, quantity, function, finish, specified product] and my Submitted tab [paste: opening, set as submitted, item, quantity, manufacturer and model, function, finish, listing reference]. Write Excel formulas (or a step-by-step Copilot plan) that match each submitted opening to its scheduled set and flag missing or extra openings, missing or extra items, quantity, function and finish differences, rated openings with no listing reference on an item, and products that differ from the specified product, then summarize flags by opening. Use only my data; do not judge equivalence or code compliance. ``` ### 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 comparison only checks the submittal against the schedule and sets you entered, so an error in your own door schedule carries through. A flag is something to look at, not a rejection, and a clean opening hasn't been checked for egress, accessibility, fire rating or security requirements. Review actions, substitutions and code questions stay with the architect and the hardware consultant. - 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? Claude or ChatGPT, then Copilot in Excel or Gemini in Google Sheets: Claude or ChatGPT reads the submitted hardware schedule into one row per item per opening; Copilot or Gemini matches it to your door schedule and specified sets and flags missing openings, item, quantity, function and finish differences and possible substitutions. A person still checks: Every flag against the submittal pages; substitutions, fire rating, egress and accessibility questions stay with the architect and hardware consultant. How do I how do I check a door hardware submittal against the door schedule and hardware sets with AI?? Export your door schedule from the model or drawings to a spreadsheet (opening number, door and frame type, fire rating, hardware set) and put the hardware sets from your specification into a Sets tab, one item per row with quantity, function and finish. Have Claude or ChatGPT read the submitted hardware schedule into a Submitted tab with one row per item per opening: opening number, set number as submitted, item, quantity, manufacturer and model, function, finish code and any rated-product listing reference shown. It copies entries exactly and writes NOT SHOWN instead of guessing. Have it list, on a separate tab, every opening in the submittal that isn't on your door schedule and every scheduled opening missing from the submittal. 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 build a building-code research checklist with AI, then verify every section?](https://aecagents.si/use-cases/code-research-architects) - [How do I restyle a massing model into AI concept images for early client talks?](https://aecagents.si/use-cases/concept-renderings) - [How do I test unit yield on a site with feasibility software before buying it?](https://aecagents.si/use-cases/site-feasibility) - [All Architect workflows](https://aecagents.si/roles/architect) - [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.