Turn signed T&M tags into a priced change order request with AI
Extra work gets lost when daily T&M tags sit in a truck until month end. Photograph each signed tag, have Claude or ChatGPT transcribe it into a fixed table (crew by trade, hours, equipment, materials, description, reference number), marking anything it cannot read as UNREADABLE, then have Copilot in Excel price the rows with the labor rates, equipment rates and markups you enter from your subcontract and roll them into a change order request log. The tags document what happened; entitlement and price still have to be agreed.
Subcontractor · Trade contracting · Claude · ChatGPT · Microsoft Excel · Microsoft Copilot
Content updated · Tool links listed below; vendor features and pricing change, so confirm with the vendor
Short answer
Use Claude or ChatGPT, then Copilot in Excel: The AI transcribes photographed T&M tags into a fixed table (UNREADABLE and UNSIGNED instead of guesses), then Copilot prices the rows only against the subcontract rates and markups you enter, rolls them into a change order request log with a flag for tags not yet on any request, and drafts cover descriptions from the tag text. Extra work gets lost when daily T&M tags sit in a truck until month end. Photograph each signed tag, have Claude or ChatGPT transcribe it into a fixed table (crew by trade, hours, equipment, materials, description, reference number), marking anything it cannot read as UNREADABLE, then have Copilot in Excel price the rows with the labor rates, equipment rates and markups you enter from your subcontract and roll them into a change order request log. The tags document what happened; entitlement and price still have to be agreed. A person still checks: every transcribed row against the tag photo and daily report, rates and markups against the subcontract, and notice deadlines; entitlement and price are negotiated by people.
AI tie-in
Tool: Claude or ChatGPT, then Copilot in Excel
The AI transcribes photographed T&M tags into a fixed table (UNREADABLE and UNSIGNED instead of guesses), then Copilot prices the rows only against the subcontract rates and markups you enter, rolls them into a change order request log with a flag for tags not yet on any request, and drafts cover descriptions from the tag text.
Prompt 1
Transcribe these signed T&M tags [upload photos or PDF] into a table with one row per line item: tag number, date, description of work, line type (labor, equipment or material), trade or classification, headcount, regular hours, overtime hours, equipment and hours, material, quantity and unit, signer's title, and reference number (change directive, RFI or field instruction). Write UNREADABLE for anything you cannot read and UNSIGNED if a tag has no signature. Do not estimate hours or quantities and do not add prices.
Prompt 2
Here is our T&M tag table [paste] and our rates tab from the subcontract: labor rate by classification, equipment rates and allowed markups [paste]. Group the tags into change order request [COR number] for [reference number], price each line using only the rates in my tab (write NO RATE where a classification or piece of equipment is missing), show labor, equipment and material subtotals, markup and total, and draft a three-sentence description from the tag text only. Do not add schedule impact or entitlement arguments.
Human check: Every transcribed row against the tag photo and daily report, rates and markups against the subcontract, and notice deadlines; entitlement and price are negotiated by people.
The problem
Turn signed T&M tags into a priced change order request with AI. This is a common, time-consuming task for a subcontractor.
What this workflow does
Extra work gets lost when daily T&M tags sit in a truck until month end. Photograph each signed tag, have Claude or ChatGPT transcribe it into a fixed table (crew by trade, hours, equipment, materials, description, reference number), marking anything it cannot read as UNREADABLE, then have Copilot in Excel price the rows with the labor rates, equipment rates and markups you enter from your subcontract and roll them into a change order request log. The tags document what happened; entitlement and price still have to be agreed.
How it works: AI drafts or analyzes. A person operates the tools, checks the work, and takes action.
Your checkpoint: A signed tag usually confirms who and what was on site, not that the work is extra or what it is worth. Entitlement, notice deadlines, rates and markups come from your subcontract, and every transcribed row needs checking against the tag photo. Not legal advice.
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
Follow the steps
- Set one field rule: every tag is filled out and signed by the customer's representative the same day, photographed before the foreman leaves site, and carries the related change directive, RFI or field instruction number.
- Upload the day's tag photos or a scanned PDF to Claude or ChatGPT and ask for one row per labor, equipment and material line, with regular and overtime hours kept separate. Unreadable values come back as UNREADABLE and tags without a signature as UNSIGNED.
- Paste the rows into an Excel log. Keep a rates tab you fill in yourself from the subcontract: labor rate by classification, equipment rates and the allowed markups. Have Copilot write the pricing formulas against that tab, never against rates the model suggests.
- Have Copilot build a change order request (COR) log: COR number, tags included, labor, equipment and material subtotals, markup, total, date submitted, status, date approved, days outstanding, and a flag for tags not yet on any COR.
- For each COR, have the model draft the cover description from the tag text only: what changed, where, the reference document and the tags attached. Add schedule impact and any reservation of rights in your own words.
- Before anything goes out, a PM checks every transcribed row against the tag photo and the daily report, and checks the notice and submission deadlines in the subcontract.
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
Transcribe these signed T&M tags [upload photos or PDF] into a table with one row per line item: tag number, date, description of work, line type (labor, equipment or material), trade or classification, headcount, regular hours, overtime hours, equipment and hours, material, quantity and unit, signer's title, and reference number (change directive, RFI or field instruction). Write UNREADABLE for anything you cannot read and UNSIGNED if a tag has no signature. Do not estimate hours or quantities and do not add prices.
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
- A signed tag usually confirms who and what was on site, not that the work is extra or what it is worth. Entitlement, notice deadlines, rates and markups come from your subcontract, and every transcribed row needs checking against the tag photo. Not legal advice.
- 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: The AI transcribes photographed T&M tags into a fixed table (UNREADABLE and UNSIGNED instead of guesses), then Copilot prices the rows only against the subcontract rates and markups you enter, rolls them into a change order request log with a flag for tags not yet on any request, and drafts cover descriptions from the tag text. A person still checks: Every transcribed row against the tag photo and daily report, rates and markups against the subcontract, and notice deadlines; entitlement and price are negotiated by people.
How do I turn signed T&M tags into a priced change order request with AI?
Set one field rule: every tag is filled out and signed by the customer's representative the same day, photographed before the foreman leaves site, and carries the related change directive, RFI or field instruction number. Upload the day's tag photos or a scanned PDF to Claude or ChatGPT and ask for one row per labor, equipment and material line, with regular and overtime hours kept separate. Unreadable values come back as UNREADABLE and tags without a signature as UNSIGNED. Paste the rows into an Excel log. Keep a rates tab you fill in yourself from the subcontract: labor rate by classification, equipment rates and the allowed markups. Have Copilot write the pricing formulas against that tab, never against rates the model suggests. 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. 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.
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.