Google Merchant Center Q&A Writer (question_and_answer feed) avatar

Google Merchant Center Q&A Writer (question_and_answer feed)

Pricing

from $14.00 / 1,000 product writtens

Go to Apify Store
Google Merchant Center Q&A Writer (question_and_answer feed)

Google Merchant Center Q&A Writer (question_and_answer feed)

Write the new Google Merchant Center question_and_answer attribute for every product from your feed or product pages. Answers use only facts from your page, Google's rules are checked, and you get a ready TSV/XML supplemental feed. Pay per product.

Pricing

from $14.00 / 1,000 product writtens

Rating

0.0

(0)

Developer

Ashish Agarwal

Ashish Agarwal

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

15 hours ago

Last modified

Share

Google Merchant Center now has a question_and_answer product attribute: up to 30 shopper questions and answers per product, used mainly in conversational shopping such as AI Mode in Google Search. This Actor writes them for your whole catalog and hands you a ready supplemental feed (TSV and XML) to add in Merchant Center.

Answers come only from your own product data. Every answer must quote a sentence from your feed or product page as proof, every number must appear on the page, and pairs that break Google's rules are thrown away. You pay only for products that get at least one valid pair.

What it does

  1. Reads your Merchant Center feed (XML, TSV/CSV or a published Google Sheets CSV) or a list of product page URLs.
  2. Opens each product page and collects facts: Product structured data (brand, material, size, weight, GTIN...), spec tables, FAQs already on the page, and the page text. Prices and offers are ignored on purpose.
  3. Asks an AI model for the questions a shopper would ask before buying, answered only from those facts.
  4. Checks every pair against Google's rules (see below) and drops the ones that fail, with the reason.
  5. Writes supplemental-feed.tsv and supplemental-feed.xml with id + question_and_answer, plus one dataset item per product with the pairs, the proof quotes and the dropped candidates.

Google's rules, checked for you

From Google's question_and_answer specification (Merchant Center Help, article 17085211):

RuleWhat this Actor does
Question and answer up to 1,000 characters eachLonger pairs are dropped (answers are written short: 1-3 sentences)
Up to 30 pairs, 10,000 characters per productHard caps (stays under 9,500 characters to be safe)
Product information only, no prices or datesDrops pairs that mention prices, currencies, discounts, dates, shipping, stock or returns
No keywords or search termsDrops keyword-list questions and ALL-CAPS text; no links, emails or markup
Answers must be correctEach answer needs a proof quote found in your facts, and every number must appear there
Don't repeat the title, description, product detail or highlightPrefers facts that aren't in them and drops answers that only repeat them (can be turned off)

Input

  • Product feed URL: your Merchant Center feed. Ids, titles, descriptions, highlights and product details come from here, so the supplemental feed matches your products exactly. Variants with the same item_group_id share one set of answers (written and charged once).
  • Product page URLs: or give pages directly. Write id, URL on a line to set the Merchant Center id yourself; otherwise the page's SKU (or GTIN, MPN or the URL, your choice) becomes the id. It must match the id in your main feed.
  • Q&A pairs per product: 6 by default, up to 30. Fewer come back when the page doesn't have enough facts: answers are never padded or guessed.
  • Language: auto writes in the page's language, or name one (English, Deutsch, Español...).

Example:

{
"productUrls": [
"SKU-123, https://shop.example/products/blue-kettle",
"https://shop.example/products/travel-mug"
],
"pairsPerProduct": 8,
"language": "auto"
}

Output

Dataset (one item per product id):

{
"id": "SKU-123",
"status": "written",
"pairCount": 2,
"pairs": [
{"question": "What is the capacity?", "answer": "It holds 1.7 L of water.", "evidence": "Capacity: 1.7 L"},
{"question": "How long does Keep Warm last?", "answer": "Keep Warm holds the chosen temperature for up to 30 minutes.",
"evidence": "Keep Warm holds the chosen temperature for up to 30 minutes."}
],
"questionAndAnswer": "\"What is the capacity?\":\"It holds 1.7 L of water.\",\"How long does Keep Warm last?\":\"Keep Warm holds the chosen temperature for up to 30 minutes.\"",
"questionAndAnswerSheets": "What is the capacity?:It holds 1.7 L of water.,How long does Keep Warm last?:Keep Warm holds the chosen temperature for up to 30 minutes.",
"dropped": [{"question": "How much does it cost?", "answer": "...", "reason": "mentions price or promotion"}]
}

Status is written (charged), skipped (not enough facts, or not a product page), no-valid-pairs or failed (page couldn't be loaded); only written is charged.

Key-value store: supplemental-feed-sheets.csv (import into a Google Sheet used as a supplemental source), supplemental-feed.tsv (Google's text syntax "question":"answer","question":"answer" with quotes doubled) and supplemental-feed.xml (RSS 2.0 with g:question_and_answer groups). questionAndAnswerSheets uses the Google Sheets syntax (no quotes; commas, colons and backslashes escaped with a backslash).

Add it to Merchant Center

  1. Run the Actor and download supplemental-feed.tsv (or .xml) from the run's Storage tab.
  2. In Merchant Center, open Data sources, add a supplemental product data source (file upload or Google Sheets) and link it to your primary source. The id column matches your products, so only question_and_answer is added.
  3. Already merging columns yourself? Use questionAndAnswer from the dataset as the value of a question_and_answer column in your own feed (or questionAndAnswerSheets in a Google Sheet).

Tip: don't also submit a document_link with the same information; Google says it extracts FAQs from such documents.

Pricing

Pay per event: one charge per product that gets at least one valid pair. Skipped, failed and no-valid-pairs products are free, variant groups are charged once, and the run stops when your spending limit is reached. Try it on 10 products first (maxProducts).

Good to know

  • Pages are loaded politely: one page at a time per store, 1.5 seconds apart, with back-off when a store answers "too many requests". A 1,000-product store takes roughly 30-40 minutes.
  • Pages that build their content only with JavaScript expose fewer facts. In feed mode the feed's own data is still used; such products may be skipped (free) rather than filled with guesses.
  • Review the answers before you submit them: you are responsible for what goes into your feed. The pairs view shows the proof quote next to every answer.

FAQ

Is the question_and_answer attribute real? Yes: it is in Google's Merchant Center product data specification (Help article 17085211), with question and answer sub-attributes, up to 30 per product.

Does it work for Shopify, WooCommerce, Magento, BigCommerce? Yes, it reads any public product page and any standard Google Shopping feed (XML/TSV/CSV). Most platforms put Product structured data on product pages.

Will it invent features? It is built not to: an answer without a proof quote from your data, or with a number that isn't in your data, is dropped and listed in dropped with the reason.

How do I add questions and answers to my Google Shopping feed? Use the question_and_answer attribute: in a text/TSV feed one cell holds "question":"answer","question":"answer", in XML each pair is a <g:question_and_answer> with <g:question> and <g:answer>. The easiest way is a supplemental data source with id + question_and_answer, which this Actor produces.

Where does Google show product Q&A? Google describes the attribute as primarily intended for conversational experiences such as AI Mode in Google Search.

More tools from the same author

Google and Google Merchant Center are trademarks of Google LLC. This Actor is independent and not affiliated with or endorsed by Google.