--- title: How do I turn settlement plate and piezometer readings into one trend workbook with rate flags using AI? | AEC Agents url: https://aecagents.si/use-cases/settlement-piezometer-readings-trend-flags description: On embankments, preloads and deep excavations the readings usually arrive as a pile of field sheets, logger CSVs and survey emails, one file per instrument, and someone rebuilds the plots by hand every week. Keep one long table of readings (instrument, date, raw value, units), one tab of instrument baselines and the action levels the engineer set, and have Copilot in Excel or Gemini in Google Sheets compute change from baseline, change since last reading and rate per week, then flag readings that cross your review or action levels or look like a bad read. Claude or ChatGPT can read scanned field sheets into the table and draft the weekly factual summary. What the movement means, and what to do about it, stays with the geotechnical engineer. last_modified: 2026-11-11 source: AEC Agents (free, open workflows; not engineering advice) --- [AI assists](https://aecagents.si/use-cases/settlement-piezometer-readings-trend-flags#honesty-labels)Workflow guide · not independently tested # How do I turn settlement plate and piezometer readings into one trend workbook with rate flags using AI? On embankments, preloads and deep excavations the readings usually arrive as a pile of field sheets, logger CSVs and survey emails, one file per instrument, and someone rebuilds the plots by hand every week. Keep one long table of readings (instrument, date, raw value, units), one tab of instrument baselines and the action levels the engineer set, and have Copilot in Excel or Gemini in Google Sheets compute change from baseline, change since last reading and rate per week, then flag readings that cross your review or action levels or look like a bad read. Claude or ChatGPT can read scanned field sheets into the table and draft the weekly factual summary. What the movement means, and what to do about it, stays with the geotechnical engineer. [Geotechnical Engineer](https://aecagents.si/roles/geotechnical-engineer) · Geotechnical · 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 computes change from baseline, change since last reading and rate per week for each instrument and flags readings that cross the levels you set, look like bad reads or are overdue; Claude or ChatGPT reads scanned field sheets into the readings table and drafts the weekly factual summary. On embankments, preloads and deep excavations the readings usually arrive as a pile of field sheets, logger CSVs and survey emails, one file per instrument, and someone rebuilds the plots by hand every week. Keep one long table of readings (instrument, date, raw value, units), one tab of instrument baselines and the action levels the engineer set, and have Copilot in Excel or Gemini in Google Sheets compute change from baseline, change since last reading and rate per week, then flag readings that cross your review or action levels or look like a bad read. Claude or ChatGPT can read scanned field sheets into the table and draft the weekly factual summary. What the movement means, and what to do about it, stays with the geotechnical engineer. A person still checks: baselines, calibration conversions, a few computed values by hand, every flag against the raw reading, and all interpretation and recommendations with the geotechnical engineer of record. ## AI tie-in **Tool:** Copilot in Excel or Gemini in Google Sheets, plus Claude or ChatGPT Copilot or Gemini computes change from baseline, change since last reading and rate per week for each instrument and flags readings that cross the levels you set, look like bad reads or are overdue; Claude or ChatGPT reads scanned field sheets into the readings table and drafts the weekly factual summary. ### Prompt 1 ``` Read these field reading sheets [upload photos or PDFs]. Build a table with one row per reading: instrument ID, date, time, raw reading, units, reader and remarks. Copy every value exactly as written. Write UNREADABLE for anything you cannot read and NOT SHOWN for anything missing. Do not convert units, fill gaps or comment on the movement. ``` ### Prompt 2 ``` Here are the headers and a few sample rows of my Instruments tab [paste: instrument ID, type, baseline value, units, review level, action level, reading interval] and my Readings tab [paste: instrument ID, date, raw reading]. Write Excel formulas (or a step-by-step Copilot plan) that add change from baseline, change since the previous reading of the same instrument and rate per week, and flag REVIEW, ACTION, CHECK READING and OVERDUE using only my levels and my interval. Do not suggest levels, limits or conversion factors from memory and do not say whether any movement is acceptable. ``` **Human check:** Baselines, calibration conversions, a few computed values by hand, every flag against the raw reading, and all interpretation and recommendations with the geotechnical engineer of record. ## The problem Turn settlement plate and piezometer readings into one trend workbook with rate flags using AI. This is a common, time-consuming task for a geotechnical engineer. ## What this workflow does On embankments, preloads and deep excavations the readings usually arrive as a pile of field sheets, logger CSVs and survey emails, one file per instrument, and someone rebuilds the plots by hand every week. Keep one long table of readings (instrument, date, raw value, units), one tab of instrument baselines and the action levels the engineer set, and have Copilot in Excel or Gemini in Google Sheets compute change from baseline, change since last reading and rate per week, then flag readings that cross your review or action levels or look like a bad read. Claude or ChatGPT can read scanned field sheets into the table and draft the weekly factual summary. What the movement means, and what to do about it, stays with the geotechnical engineer. **How it works:** AI drafts or analyzes. A person operates the tools, checks the work, and takes action. **Your checkpoint:** The workbook only does arithmetic on your readings against levels you set. It does not judge stability, consolidation, whether a preload can come off or whether excavation can continue. Baselines, conversions, action levels and every interpretation and recommendation are decisions for the geotechnical engineer of record. ## 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 an Instruments tab: instrument ID, type (settlement plate, survey point, standpipe or vibrating wire piezometer), location or station, installation date, baseline date and baseline value, units, and the review and action levels your monitoring plan sets for that instrument. You type the levels; the AI never proposes them. 2. Keep a Readings tab as one long table: instrument ID, date and time, raw reading, units, who read it and a remarks column. Paste logger CSV exports straight in. For handwritten or scanned field sheets, have Claude or ChatGPT read them into the same columns, copying values exactly and writing UNREADABLE instead of guessing. 3. Have Copilot in Excel or Gemini in Google Sheets add, per reading, change from baseline, change since the previous reading, days between readings and rate per week, and convert piezometer readings to the same quantity you report (head or pressure) using conversion inputs you type from the instrument's calibration sheet. 4. Add flags: REVIEW and ACTION where a value or rate crosses the levels on the Instruments tab, CHECK READING where a change reverses sign sharply or jumps far beyond the instrument's recent spread, and OVERDUE where an instrument has not been read within the interval you set. 5. Build one chart per instrument (value and fill height or excavation stage against time, if you log those) and a one-page status table: last reading, change, rate, flag. Add rainfall from your own site gauge or a public record as a separate column if it helps explain piezometer swings. 6. Have Claude or ChatGPT draft the weekly factual summary from the status table: which instruments moved, by how much, which flags are open and which readings need re-reading. The engineer edits it and adds any interpretation or recommendation. ## 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 Instruments tab [paste: instrument ID, type, location, baseline date, baseline value, units, review level, action level, reading interval in days] and my Readings tab [paste: instrument ID, date, raw reading, units, remarks]. Write Excel formulas (or a step-by-step Copilot plan) that add, for each reading, change from baseline, change since the previous reading of the same instrument, days since that reading and rate per week. Flag REVIEW or ACTION where the change or rate crosses the levels on my Instruments tab, CHECK READING where the change since the previous reading is more than three times the average absolute change of that instrument's last five readings, and OVERDUE where an instrument's latest reading is older than its interval as of the date in Settings!B1. Then build a status table with one row per instrument showing the latest values and open flags. Use only my data and my levels; do not suggest action levels, settlement limits or conversion factors from memory, and do not say whether any movement is acceptable. ``` ### 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 does arithmetic on your readings against levels you set. It does not judge stability, consolidation, whether a preload can come off or whether excavation can continue. Baselines, conversions, action levels and every interpretation and recommendation are decisions for the geotechnical engineer of record. - 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 computes change from baseline, change since last reading and rate per week for each instrument and flags readings that cross the levels you set, look like bad reads or are overdue; Claude or ChatGPT reads scanned field sheets into the readings table and drafts the weekly factual summary. A person still checks: Baselines, calibration conversions, a few computed values by hand, every flag against the raw reading, and all interpretation and recommendations with the geotechnical engineer of record. How do I how do I turn settlement plate and piezometer readings into one trend workbook with rate flags using AI?? Set up an Instruments tab: instrument ID, type (settlement plate, survey point, standpipe or vibrating wire piezometer), location or station, installation date, baseline date and baseline value, units, and the review and action levels your monitoring plan sets for that instrument. You type the levels; the AI never proposes them. Keep a Readings tab as one long table: instrument ID, date and time, raw reading, units, who read it and a remarks column. Paste logger CSV exports straight in. For handwritten or scanned field sheets, have Claude or ChatGPT read them into the same columns, copying values exactly and writing UNREADABLE instead of guessing. Have Copilot in Excel or Gemini in Google Sheets add, per reading, change from baseline, change since the previous reading, days between readings and rate per week, and convert piezometer readings to the same quantity you report (head or pressure) using conversion inputs you type from the instrument's calibration sheet. 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 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 field density test reports into a compaction log by area and lift and flag tests for review with AI?](https://aecagents.si/use-cases/compaction-test-log-by-area-lift) - [All Geotechnical Engineer workflows](https://aecagents.si/roles/geotechnical-engineer) - [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.