Fieldbook to AIThe plain-English guide to which AI to use

Time-savers

Turn web pages into a spreadsheet

Point it at product, job or listing pages and get tidy rows of data in a spreadsheet, at a tiny cost per page.

Last updated .

Costs here use the prices AI companies charge software developers, so they show relative cost, not your monthly bill. See what ChatGPT, Claude and Gemini charge you.

Starter recipe, not yet tested end to end.

What it does for you

Reads a web page and pulls out the details you care about (name, price, location and so on) into columns, leaving a field blank rather than guessing.

Time saved

Replaces copying and pasting from page to page. We have not measured the time saved yet.

What it costs to run

Model to start withCost for 1,000 pages
Schematron V2 Turbo$0.26 (about 26 cents)
DeepSeek V4.1 Flash$1.20

This is a narrow job, so a purpose-built tiny model or a very cheap one does it for a fraction of the price of the top models. Estimate assumes about 6,000 tokens in and 500 tokens out per item (a token is about three-quarters of a word), at list prices. Real usage will differ.

How to build it

You will need: Make or n8n (automation apps); Google Sheets

  1. Download the page's content.
  2. Strip out menus, scripts and styling.
  3. Send the content and a list of the columns you want to the AI model.
  4. Add the result as a new row. If a result looks broken, try once more.

Instructions to give the AI

Pull these fields from the page below and return them as JSON: {{fields}}. Use null for anything that is missing. Do not guess. Page:
{{page}}