The Scenario
You're an e-commerce analyst and you've spent the morning building out your competitor tracking workbook. Column A has 500 product URLs — real pages, not search results — and you need to pull the product name, current price, and stock status from each one into columns B through D by end of day.
The bad version:
- Open each URL in a browser, manually read the price and availability, type it into the workbook one row at a time
- Export the URL list as a CSV, upload it to Agenty, configure the agent's CSS selectors, wait for the job to finish, download the output, open it in a separate spreadsheet, manually match it back to the original rows
- Get through the first 80 rows before realizing the "in_stock" field returned "True" in some rows and "true" in others, spend 20 minutes normalizing before the rest of the job even finishes
Five hundred rows of that is not analysis — it's transcription. And your afternoon was supposed to be spent on the insights, not the collection.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent built into your Excel workbook. It reads your data, understands what's in each column, and talks to Agenty on your behalf. You describe what you want, and the extraction runs directly from the sidebar.
Scrape the product name, price, and in-stock status from every URL in column A using Agenty and write the results into columns B, C, and D
What You Get
- Column B: product name as it appears in the page title or primary heading element
- Column C: price extracted from the pricing element — formatted as returned (you can ask for normalization in the same prompt)
- Column D: in-stock status — "true," "false," or the exact availability string from the page
- Rows that return a scraping error get flagged in column E so you can rerun them separately
What If the Data Is Not Quite Ready
The CSS selectors are inconsistent across your URL list
Scrape the product name from column A — if the standard title selector returns nothing, fall back to the first H1 on the page — write results into column B and mark any rows where the fallback was used in column C
The prices come back in different currency formats
Scrape the price from each URL in column A using Agenty, normalize all values to USD decimal format (e.g., 29.99 not $29.99 or 29,99), and write the cleaned price into column B
Some URLs are in a different worksheet
Combine URLs from the 'Main Products' worksheet column A and the 'New SKUs' worksheet column A, scrape name, price, and stock status from each using Agenty, and write the results into a new 'Scraped Results' sheet starting at row 2
Clean the list, scrape, and flag outliers in one pass
Filter column A to rows where column E is blank (not previously scraped), scrape name, price, and stock status using Agenty, write results into B, C, D, and flag any product priced below $5 or above $500 in column F as a potential data error
The pattern: filtering the scope, running the extraction, and marking exceptions all happen in the same prompt — you don't need three separate runs.
Try It
Get the 7-day free trial of SheetXAI and open any Excel workbook with a column of product URLs — then ask it to pull name, price, and availability from each one using Agenty. When you're done, check out how to extract structured metadata from URLs or see the full Agenty integration overview.