--- title: How do I track owner contingency drawdown against percent complete with AI? | AEC Agents url: https://aecagents.si/use-cases/contingency-drawdown-vs-percent-complete description: Owners usually learn the contingency is gone at the monthly meeting where the last of it is spent. Keep a ledger of every approved draw on the owner's contingency (date, amount, change reference, reason category) and the project's percent complete from the approved pay applications, and have Copilot in Excel or Gemini in Google Sheets compute the running balance, share of contingency used, share of work complete and the gap between the two, by month. Claude or ChatGPT can sort draws into reason categories you define (unforeseen conditions, design changes, owner scope, allowance overruns) and draft the one-page monthly note. How much contingency is enough, and what to do about a gap, stays with the owner and the team. last_modified: 2026-11-11 source: AEC Agents (free, open workflows; not engineering advice) --- [AI assists](https://aecagents.si/use-cases/contingency-drawdown-vs-percent-complete#honesty-labels)Workflow guide · not independently tested # How do I track owner contingency drawdown against percent complete with AI? Owners usually learn the contingency is gone at the monthly meeting where the last of it is spent. Keep a ledger of every approved draw on the owner's contingency (date, amount, change reference, reason category) and the project's percent complete from the approved pay applications, and have Copilot in Excel or Gemini in Google Sheets compute the running balance, share of contingency used, share of work complete and the gap between the two, by month. Claude or ChatGPT can sort draws into reason categories you define (unforeseen conditions, design changes, owner scope, allowance overruns) and draft the one-page monthly note. How much contingency is enough, and what to do about a gap, stays with the owner and the team. [Owner](https://aecagents.si/roles/owner) · Owner & development · 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 builds the monthly contingency ledger: running balance, percent of contingency used against percent complete from approved pay applications, balance after pending changes and draws by reason; Claude or ChatGPT proposes reason categories for each draw and drafts the monthly owner note. Owners usually learn the contingency is gone at the monthly meeting where the last of it is spent. Keep a ledger of every approved draw on the owner's contingency (date, amount, change reference, reason category) and the project's percent complete from the approved pay applications, and have Copilot in Excel or Gemini in Google Sheets compute the running balance, share of contingency used, share of work complete and the gap between the two, by month. Claude or ChatGPT can sort draws into reason categories you define (unforeseen conditions, design changes, owner scope, allowance overruns) and draft the one-page monthly note. How much contingency is enough, and what to do about a gap, stays with the owner and the team. A person still checks: every draw against the executed change orders, percent complete against the approved pay applications, the categories, and any forecast or budget decision with the owner's rep and project team. ## AI tie-in **Tool:** Copilot in Excel or Gemini in Google Sheets, plus Claude or ChatGPT Copilot or Gemini builds the monthly contingency ledger: running balance, percent of contingency used against percent complete from approved pay applications, balance after pending changes and draws by reason; Claude or ChatGPT proposes reason categories for each draw and drafts the monthly owner note. ### Prompt 1 ``` Here is my list of approved contingency draws [paste: date, amount, change reference, description] and my reason categories [paste list with one-line definitions]. Propose one category per draw in a table, marking REVIEW where the description fits more than one category or none. Do not change amounts, combine draws or add categories. ``` ### Prompt 2 ``` Here are the headers and a few sample rows of my Draws, Pending and Progress tabs [paste]. Settings!B1 is the opening contingency. Write Excel formulas (or a step-by-step Copilot plan) for a monthly table with draws in the month, cumulative drawn, remaining balance, percent of contingency used, percent complete, the gap between them and the balance after pending changes, plus totals by reason category. Use only my data; do not forecast, suggest a contingency percentage or say whether the remainder is enough. ``` **Human check:** Every draw against the executed change orders, percent complete against the approved pay applications, the categories, and any forecast or budget decision with the owner's rep and project team. ## The problem Track owner contingency drawdown against percent complete with AI. This is a common, time-consuming task for a owner. ## What this workflow does Owners usually learn the contingency is gone at the monthly meeting where the last of it is spent. Keep a ledger of every approved draw on the owner's contingency (date, amount, change reference, reason category) and the project's percent complete from the approved pay applications, and have Copilot in Excel or Gemini in Google Sheets compute the running balance, share of contingency used, share of work complete and the gap between the two, by month. Claude or ChatGPT can sort draws into reason categories you define (unforeseen conditions, design changes, owner scope, allowance overruns) and draft the one-page monthly note. How much contingency is enough, and what to do about a gap, stays with the owner and the team. **How it works:** AI drafts or analyzes. A person operates the tools, checks the work, and takes action. **Your checkpoint:** The workbook reports what has been drawn against what has been built, from records you control. It does not forecast cost to complete, judge whether a change was justified or decide whether the contingency is adequate. Approvals, categories, forecasts and any decision about the budget stay with the owner, the owner's rep and the project team. ## 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 up a Settings tab with the opening contingency amount (or separate amounts if you hold design, construction and owner contingencies) and the reporting month. 2. Keep a Draws tab, one row per approved draw: date approved, amount, change order or directive reference, a short description, which contingency it came from, and a reason category from a short list you define. Pending changes go in a separate Pending tab with their estimated amounts, never in the ledger. 3. Have Claude or ChatGPT propose a reason category for each draw from its description, marking REVIEW where the description fits more than one. You confirm each category. 4. Keep a Progress tab with percent complete by month taken from the approved pay applications or your owner's rep report, with the source noted. 5. Have Copilot in Excel or Gemini in Google Sheets build the monthly table: draws this month, cumulative drawn, remaining balance, percent of contingency used, percent of work complete, the gap between them, and a second balance that also subtracts pending changes. Add a chart of both percentages over time and a summary of draws by reason category. 6. Have Claude or ChatGPT draft a one-page factual note for the monthly owner meeting from that table. Edit it yourself and keep conclusions and recommendations for the people who own the budget. ## 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 Draws tab [paste: date approved, amount, change reference, description, contingency bucket, reason category], my Pending tab [paste: reference, description, estimated amount] and my Progress tab [paste: month, percent complete, source]. Settings!B1 is the opening contingency and Settings!B2 the reporting month. Write Excel formulas (or a step-by-step Copilot plan) that build a monthly table with draws in the month, cumulative drawn, remaining balance, percent of contingency used, percent complete, and percent used minus percent complete, plus a remaining balance after pending changes. Add a summary of drawn amounts by reason category and by contingency bucket. Use only my data; do not estimate future draws, do not suggest a contingency percentage and do not say whether the remaining amount is enough. ``` ### 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 reports what has been drawn against what has been built, from records you control. It does not forecast cost to complete, judge whether a change was justified or decide whether the contingency is adequate. Approvals, categories, forecasts and any decision about the budget stay with the owner, the owner's rep and the project team. - 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 builds the monthly contingency ledger: running balance, percent of contingency used against percent complete from approved pay applications, balance after pending changes and draws by reason; Claude or ChatGPT proposes reason categories for each draw and drafts the monthly owner note. A person still checks: Every draw against the executed change orders, percent complete against the approved pay applications, the categories, and any forecast or budget decision with the owner's rep and project team. How do I how do I track owner contingency drawdown against percent complete with AI?? Set up a Settings tab with the opening contingency amount (or separate amounts if you hold design, construction and owner contingencies) and the reporting month. Keep a Draws tab, one row per approved draw: date approved, amount, change order or directive reference, a short description, which contingency it came from, and a reason category from a short list you define. Pending changes go in a separate Pending tab with their estimated amounts, never in the ledger. Have Claude or ChatGPT propose a reason category for each draw from its description, marking REVIEW where the description fits more than one. You confirm each category. 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 compare site captures to the plan with AI progress tracking?](https://aecagents.si/use-cases/progress-tracking) - [How do I capture existing conditions and as-builts with 3D scanning?](https://aecagents.si/use-cases/as-built-capture) - [How do I review quality and progress remotely with AI-analyzed site captures?](https://aecagents.si/use-cases/remote-quality-control) - [All Owner workflows](https://aecagents.si/roles/owner) - [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.