--- title: How do I turn field density test reports into a compaction log by area and lift and flag tests for review with AI? | AEC Agents url: https://aecagents.si/use-cases/compaction-test-log-by-area-lift description: Field density results come back as daily PDF reports or paper tickets, one per visit, and the office still retypes them to answer the questions that matter: which areas and lifts have been tested, which tests fell below the requirement, and whether each failed test was followed by a passing retest at the same spot. Have Claude or ChatGPT read the reports into one row per test, keep the moisture-density (Proctor) references in their own tab, and use Copilot in Excel to compute percent compaction from the values on the report, compare it with the requirement you typed in from the project specification, and list open failures and untested lifts. Acceptance of the fill and any corrective action stay with the geotechnical engineer of record. last_modified: 2026-11-11 source: AEC Agents (free, open workflows; not engineering advice) --- [AI assists](https://aecagents.si/use-cases/compaction-test-log-by-area-lift#honesty-labels)Workflow guide · not independently tested # How do I turn field density test reports into a compaction log by area and lift and flag tests for review with AI? Field density results come back as daily PDF reports or paper tickets, one per visit, and the office still retypes them to answer the questions that matter: which areas and lifts have been tested, which tests fell below the requirement, and whether each failed test was followed by a passing retest at the same spot. Have Claude or ChatGPT read the reports into one row per test, keep the moisture-density (Proctor) references in their own tab, and use Copilot in Excel to compute percent compaction from the values on the report, compare it with the requirement you typed in from the project specification, and list open failures and untested lifts. Acceptance of the fill and any corrective action stay with the geotechnical engineer of record. [Geotechnical Engineer](https://aecagents.si/roles/geotechnical-engineer) · Geotechnical · Claude · ChatGPT · Microsoft Excel · Microsoft Copilot 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: The AI reads field density reports into one row per test (UNREADABLE instead of guesses), then Copilot recomputes percent compaction from the referenced Proctor value, compares it with the requirement you typed in by area, marks CHECK items, chains retests to failures and shows untested lifts. Field density results come back as daily PDF reports or paper tickets, one per visit, and the office still retypes them to answer the questions that matter: which areas and lifts have been tested, which tests fell below the requirement, and whether each failed test was followed by a passing retest at the same spot. Have Claude or ChatGPT read the reports into one row per test, keep the moisture-density (Proctor) references in their own tab, and use Copilot in Excel to compute percent compaction from the values on the report, compare it with the requirement you typed in from the project specification, and list open failures and untested lifts. Acceptance of the fill and any corrective action stay with the geotechnical engineer of record. A person still checks: every transcribed value and Proctor reference against the source reports, and the requirements against the specification; acceptance and corrective action by the geotechnical engineer of record. ## AI tie-in **Tool:** Claude or ChatGPT, then Copilot in Excel The AI reads field density reports into one row per test (UNREADABLE instead of guesses), then Copilot recomputes percent compaction from the referenced Proctor value, compares it with the requirement you typed in by area, marks CHECK items, chains retests to failures and shows untested lifts. ### Prompt 1 ``` Read these field density test reports [upload PDFs or photos]. Build a table with one row per test: file name, page, report number, date, test number, area or station, elevation or lift, material description, Proctor or reference ID used, test method, wet density, moisture content, dry density, percent compaction as reported, required value if printed, any oversize correction noted, and retest-of number if marked. Copy values and units exactly as printed. Write UNREADABLE for anything you cannot read and NOT SHOWN for anything missing. Do not judge whether any test passes and do not supply any requirement or Proctor value from memory. ``` ### Prompt 2 ``` Here is my tests tab [paste], my Proctor tab with the lab-reported maximum dry density and optimum moisture for each reference ID [paste], and my criteria tab with required percent compaction, moisture range and testing frequency by area, typed by me from the project specification and geotechnical report [paste]. Use only these values. Write Excel formulas or a step-by-step Copilot plan that recomputes percent compaction for each test, shows its difference from the reported value, and marks CHECK where a test is below my requirement, outside my moisture range, uses a Proctor ID not in my tab, or differs from the reported value. Then list failed tests with no later passing retest at the same area and lift, and lifts with fewer tests than my frequency. Never write accepted or passed. ``` **Human check:** Every transcribed value and Proctor reference against the source reports, and the requirements against the specification; acceptance and corrective action by the geotechnical engineer of record. ## The problem Turn field density test reports into a compaction log by area and lift and flag tests for review with AI. This is a common, time-consuming task for a geotechnical engineer. ## What this workflow does Field density results come back as daily PDF reports or paper tickets, one per visit, and the office still retypes them to answer the questions that matter: which areas and lifts have been tested, which tests fell below the requirement, and whether each failed test was followed by a passing retest at the same spot. Have Claude or ChatGPT read the reports into one row per test, keep the moisture-density (Proctor) references in their own tab, and use Copilot in Excel to compute percent compaction from the values on the report, compare it with the requirement you typed in from the project specification, and list open failures and untested lifts. Acceptance of the fill and any corrective action stay with the geotechnical engineer of record. **How it works:** AI drafts or analyzes. A person operates the tools, checks the work, and takes action. **Your checkpoint:** The log organizes test results and compares them with requirements you entered; it does not accept fill or decide corrective action. Requirements come from the project specification and the geotechnical report, and the engineer of record decides what a low test means. Check every transcribed value and every Proctor reference against the source reports. ## 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) ## Follow the steps 1. Set up one workbook per job with three tabs: a Proctor tab (reference ID, material description, test method, maximum dry density and optimum moisture as reported by the lab), a tests tab (one row per field test) and a criteria tab you fill in yourself from the project specification and geotechnical report: required percent compaction and moisture range by area or fill type, and testing frequency if specified. Tell the model not to supply any of these from memory. 2. Upload the daily field reports to Claude or ChatGPT and have it fill the tests tab exactly as printed: report number, date, test number, area or station, elevation or lift, material, Proctor reference used, test method, wet density, moisture, dry density, percent compaction as reported, and retest-of number if marked, with the file and page. UNREADABLE instead of guesses. 3. Have Copilot in Excel recompute percent compaction from the dry density and the referenced Proctor value, show the difference from the reported value, and look up the requirement for that area from your criteria tab. Mark CHECK where a test is below your entered requirement, outside your moisture range, references a Proctor ID not in the Proctor tab, or where the recomputed and reported values differ. Oversize corrections are taken from the report, not recomputed by the AI. 4. Chain retests: for every CHECK test, find a later test marked as its retest or at the same area and lift, and list failures with no later passing test as open. 5. Build a coverage view by area and lift (tests per lift, last test date) and compare it with the testing frequency in your criteria tab, so untested lifts show up before they are buried. 6. Send open items to the engineer of record the way the project requires, with the field reports attached. Have the model draft a factual weekly summary from the log only: tests run, CHECK items, open failures and coverage gaps. ## 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 ``` Read these field density test reports [upload PDFs or photos]. Build a table with one row per test: file name, page, report number, date, test number, area or station, elevation or lift, material description, Proctor or reference ID used, test method, wet density, moisture content, dry density, percent compaction as reported, required value if printed, any oversize correction noted, and retest-of number if marked. Copy values and units exactly as printed. Write UNREADABLE for anything you cannot read and NOT SHOWN for anything missing. Do not judge whether any test passes and do not supply any requirement or Proctor value from memory. ``` ### 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 log organizes test results and compares them with requirements you entered; it does not accept fill or decide corrective action. Requirements come from the project specification and the geotechnical report, and the engineer of record decides what a low test means. Check every transcribed value and every Proctor reference against the source reports. - 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 reads field density reports into one row per test (UNREADABLE instead of guesses), then Copilot recomputes percent compaction from the referenced Proctor value, compares it with the requirement you typed in by area, marks CHECK items, chains retests to failures and shows untested lifts. A person still checks: Every transcribed value and Proctor reference against the source reports, and the requirements against the specification; acceptance and corrective action by the geotechnical engineer of record. How do I how do I turn field density test reports into a compaction log by area and lift and flag tests for review with AI?? Set up one workbook per job with three tabs: a Proctor tab (reference ID, material description, test method, maximum dry density and optimum moisture as reported by the lab), a tests tab (one row per field test) and a criteria tab you fill in yourself from the project specification and geotechnical report: required percent compaction and moisture range by area or fill type, and testing frequency if specified. Tell the model not to supply any of these from memory. Upload the daily field reports to Claude or ChatGPT and have it fill the tests tab exactly as printed: report number, date, test number, area or station, elevation or lift, material, Proctor reference used, test method, wet density, moisture, dry density, percent compaction as reported, and retest-of number if marked, with the file and page. UNREADABLE instead of guesses. Have Copilot in Excel recompute percent compaction from the dry density and the referenced Proctor value, show the difference from the reported value, and look up the requirement for that area from your criteria tab. Mark CHECK where a test is below your entered requirement, outside your moisture range, references a Proctor ID not in the Proctor tab, or where the recomputed and reported values differ. Oversize corrections are taken from the report, not recomputed by the AI. 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. ## Where to go next - [How do I turn PDF or scanned borehole logs into a reviewable spreadsheet?](https://aecagents.si/use-cases/borehole-log-to-spreadsheet) - [How do I turn raw CPT sounding files into one consistent workbook and profile plots with an AI-written script?](https://aecagents.si/use-cases/cpt-files-to-workbook-plots) - [How do I turn settlement plate and piezometer readings into one trend workbook with rate flags using AI?](https://aecagents.si/use-cases/settlement-piezometer-readings-trend-flags) - [All Geotechnical Engineer workflows](https://aecagents.si/roles/geotechnical-engineer) - [All Field, quality and safety workflows](https://aecagents.si/tasks/field-safety) ## 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) ## 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.