AI assistsWorkflow guide · not independently tested

Turn PDF or scanned borehole logs into a reviewable spreadsheet

Upload a borehole log PDF to Claude or ChatGPT, have it extract depths, strata descriptions, SPT or RQD values and groundwater notes into a fixed column layout, then spot-check every row against the PDF before you import anything into gINT, OpenGround or your own workbook.

Geotechnical Engineer · Geotechnical · Claude · ChatGPT · Microsoft Excel

Content updated · Tool links listed below; vendor features and pricing change, so confirm with the vendor

Short answer

Use Claude or ChatGPT: The AI reads the borehole log PDF and fills your column template, citing the page and marking unreadable cells UNVERIFIED. Upload a borehole log PDF to Claude or ChatGPT, have it extract depths, strata descriptions, SPT or RQD values and groundwater notes into a fixed column layout, then spot-check every row against the PDF before you import anything into gINT, OpenGround or your own workbook. A person still checks: every depth and test value against the PDF; poor scans and handwriting need a person.

AI tie-in

Tool: Claude or ChatGPT

The AI reads the borehole log PDF and fills your column template, citing the page and marking unreadable cells UNVERIFIED.

Prompt 1

Extract this borehole log into a table with columns: borehole ID, top depth, bottom depth, material description, consistency/density, SPT N or RQD, groundwater, remarks. Cite the PDF page for every value. If a value is unreadable, write UNVERIFIED. Do not invent depths or test values: [upload PDF]

Prompt 2

Here is the extracted table and the source PDF page text. List every row where depth continuity breaks, where SPT/RQD is blank but the log shows a test, or where you wrote UNVERIFIED, so I can re-check those cells: [paste table]

Human check: Every depth and test value against the PDF; poor scans and handwriting need a person.

The problem

Turn PDF or scanned borehole logs into a reviewable spreadsheet. This is a common, time-consuming task for a geotechnical engineer.

What this workflow does

Upload a borehole log PDF to Claude or ChatGPT, have it extract depths, strata descriptions, SPT or RQD values and groundwater notes into a fixed column layout, then spot-check every row against the PDF before you import anything into gINT, OpenGround or your own workbook.

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

Your checkpoint: Handwritten and poor scans fail often. Every depth and test value needs a person with the PDF open; this does not replace 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

Follow the steps

  1. Define the target columns first (borehole ID, top depth, bottom depth, material description, consistency or density, SPT N or RQD, groundwater, remarks).
  2. Upload one log PDF and ask the model to fill only those columns, citing the page for each value.
  3. Require UNVERIFIED instead of a guess when a cell cannot be read.
  4. Spot-check depths for continuity (no gaps or overlaps) and re-read any UNVERIFIED rows on the PDF.
  5. Only then paste into Excel or your logging software import template.
  6. Keep confidential client logs on tools your company has approved.

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

Extract this borehole log into a table with columns: borehole ID, top depth, bottom depth, material description, consistency/density, SPT N or RQD, groundwater, remarks. Cite the PDF page for every value. If a value is unreadable, write UNVERIFIED. Do not invent depths or test values: [upload PDF]

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

  • Handwritten and poor scans fail often. Every depth and test value needs a person with the PDF open; this does not replace 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?

Claude or ChatGPT: The AI reads the borehole log PDF and fills your column template, citing the page and marking unreadable cells UNVERIFIED. A person still checks: Every depth and test value against the PDF; poor scans and handwriting need a person.

How do I turn PDF or scanned borehole logs into a reviewable spreadsheet?

Define the target columns first (borehole ID, top depth, bottom depth, material description, consistency or density, SPT N or RQD, groundwater, remarks). Upload one log PDF and ask the model to fill only those columns, citing the page for each value. Require UNVERIFIED instead of a guess when a cell cannot be read. 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. 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. It is written from vendor documentation and practitioner use.

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.

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.