How do I reconcile unit-price field tickets against bid quantities with AI?

Short answer

Use Claude or ChatGPT, then Copilot in Excel or Gemini in Google Sheets: Claude or ChatGPT reads unit-price field and delivery tickets into one Tickets table and proposes bid-item matches; Copilot or Gemini totals tickets this period and to date per bid item, computes remaining quantity and dollars, and flags overruns, unmatched tickets, unit mismatches and duplicate ticket numbers. Field tickets and delivery tickets for unit-price work (excavation, haul, stone, paving, undercut) pile up while the bid quantities and remaining balances live in another spreadsheet. By the time someone notices an overrun, the tickets are already approved. Have Claude or ChatGPT read the tickets into one table, and have Copilot in Excel or Gemini in Google Sheets compare them with the bid quantities, prior tickets and remaining balance so overruns and unmatched items surface before the pay app goes out. Whether a ticket is payable, and whether an overrun is a change, stays with the estimator and the PM. A person still checks: every match and every flag with the estimator and PM before the pay app is billed; payability and change orders stay with them under the contract.

AI tie-in

Tool: Claude or ChatGPT, then Copilot in Excel or Gemini in Google Sheets

Claude or ChatGPT reads unit-price field and delivery tickets into one Tickets table and proposes bid-item matches; Copilot or Gemini totals tickets this period and to date per bid item, computes remaining quantity and dollars, and flags overruns, unmatched tickets, unit mismatches and duplicate ticket numbers.

Prompt 1

Read these unit-price field or delivery tickets [upload]. Build a table with one row per ticket line: date, ticket number, item as written, location or station if shown, quantity, unit, truck or source if shown, and signed-by. Copy quantities exactly and write NOT SHOWN instead of guessing. Then propose a match from each ticket line to this bid schedule [paste: item, unit, bid quantity, unit price] with a confidence word (clear, likely, unsure). Do not decide whether a ticket is payable.

Prompt 2

Here are the headers and a few sample rows of my Bid tab [paste: item, unit, bid quantity, unit price], my Prior tab [paste: item, approved quantity to date] and my Tickets tab [paste: date, ticket number, item as written, quantity, unit, matched bid item]. Write Excel formulas (or a step-by-step Copilot plan) that total tickets this period and to date per bid item, compute remaining quantity and dollars at the bid unit price, and flag items over the bid quantity, unmatched tickets, unit mismatches and duplicate ticket numbers. Use only my data; do not decide whether a ticket is payable.

Human check: Every match and every flag with the estimator and PM before the pay app is billed; payability and change orders stay with them under the contract.

The problem

Reconcile unit-price field tickets against bid quantities with AI. This is a common, time-consuming task for a estimator.

What this workflow does

Field tickets and delivery tickets for unit-price work (excavation, haul, stone, paving, undercut) pile up while the bid quantities and remaining balances live in another spreadsheet. By the time someone notices an overrun, the tickets are already approved. Have Claude or ChatGPT read the tickets into one table, and have Copilot in Excel or Gemini in Google Sheets compare them with the bid quantities, prior tickets and remaining balance so overruns and unmatched items surface before the pay app goes out. Whether a ticket is payable, and whether an overrun is a change, stays with the estimator and the PM.

How it works: AI drafts or analyzes. A person operates the tools, checks the work, and takes action.

Your checkpoint: The workbook only compares tickets with the bid quantities you entered. A ticket can be valid extra work, a mis-coded item or a bad measure, so a flag is a question for the PM, not a rejection. Payability, unit-price interpretation and change orders stay with the estimator and the project manager under the contract.

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

Export the unit-price bid schedule (item, unit, bid quantity, unit price) and any prior approved ticket totals by item, and collect this period's field or delivery tickets (PDF, photos or app export).
Have Claude or ChatGPT read every ticket into a Tickets tab: date, ticket number, item as written, location or station if shown, quantity, unit, truck or source if shown, and signed-by. It copies quantities exactly and writes NOT SHOWN instead of guessing.
Have it propose a match from each ticket line to a bid item using item wording and unit, with a confidence word (clear, likely, unsure). You fix the unsure ones.
Have Copilot in Excel or Gemini in Google Sheets compute, per bid item, tickets this period, tickets to date, remaining bid quantity and dollars at the bid unit price.
Flag items over the bid quantity, tickets with no matched bid item, tickets whose unit doesn't match the bid unit, duplicate ticket numbers, and items burning faster than percent complete if you enter one.
Send the flagged list to the PM before the pay app is billed, and keep the Tickets tab as backup for the quantities claimed.

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 Bid tab [paste: item, unit, bid quantity, unit price], my Prior tab [paste: item, approved quantity to date] and my Tickets tab [paste: date, ticket number, item as written, quantity, unit, matched bid item]. Write Excel formulas (or a step-by-step Copilot plan) that total tickets this period and to date per bid item, compute remaining quantity and dollars at the bid unit price, and flag items over the bid quantity, unmatched tickets, unit mismatches and duplicate ticket numbers. Use only my data; do not decide whether a ticket is payable.

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 workbook only compares tickets with the bid quantities you entered. A ticket can be valid extra work, a mis-coded item or a bad measure, so a flag is a question for the PM, not a rejection. Payability, unit-price interpretation and change orders stay with the estimator and the project manager under the contract.
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 unit-price field and delivery tickets into one Tickets table and proposes bid-item matches; Copilot or Gemini totals tickets this period and to date per bid item, computes remaining quantity and dollars, and flags overruns, unmatched tickets, unit mismatches and duplicate ticket numbers. A person still checks: Every match and every flag with the estimator and PM before the pay app is billed; payability and change orders stay with them under the contract.