How it works
What this workflow does
Turn a SKU and approved product facts into listing copy an editor can review. An authenticated webhook validates the brief, drafts a headline, description, feature bullets, and search metadata with OpenAI, and verifies that every bullet cites approved facts before writing to Google Sheets.
The workflow imports inactive with dryRun: true. Run with sample data uses a fictional desk tray and sample copy, so the preview does not call OpenAI or Google Sheets.
This is the product-content layer for the Content Publishing, Social Distribution & Newsletter Intelligence blueprint; the E-Commerce Cart Recovery & Checkout Intelligence blueprint covers the commerce journey after the listing is live.
Approved facts only
Validate product brief requires a stable request ID, SKU, product name, audience, and three to twelve approved facts. Each fact needs a short label and value. The workflow numbers the facts so the model can reference them.
The model returns a headline, description, three to five feature bullets, an SEO title of at most 60 characters, and an SEO description of at most 155 characters. Every bullet must cite one or more supplied fact IDs. Plain text is required; links, HTML, and unsupported numbers are rejected.
Verify product copy also checks numeric claims. Any number in the headline, description, SEO fields, or bullets must appear in the product name or one of the approved fact values. This catches an invented size or specification before the sheet is written.
Review queue and replays
The Product Copy Queue is keyed by Request ID. If a row already exists, the workflow stops and leaves the existing draft and editorial status intact. Use a fresh request ID for a new revision.
A successful draft is saved with the feature bullets, SEO metadata, the Fact References evidence trail, and Status: Needs review. The editor compares the wording to the product record before copying it into the catalog.
Validation scope
The supplied report confirms the isolated n8n 2.47.4 import, inactive state, and sample path. It also covers structural checks, fact-reference validation, invented dimensions and numeric claims, unknown fact IDs, and existing-request recognition. Live OpenAI and Google Sheets calls require a staging test with your accounts.
How to use
Before you start
- A current n8n instance.
- An OpenAI API key and a JSON-mode model.
- A Google spreadsheet tab for the product copy queue.
- A Google Sheets OAuth credential.
- A trusted content queue or internal form that can send the authenticated payload.
1. Import and run the sample
Download the complete package, extract the ZIP, and read the full setup guide. Import product-listing-copy.n8n.json and keep it inactive.
Open Run with sample data and choose Test workflow. Verify product copy should return three feature bullets with their fact references and the SEO fields.
2. Create the queue
Create a tab named Product Copy Queue with these exact headers:
| Request ID | SKU | Headline | Description | Features | SEO Title | SEO Description | Fact References | Status |
|---|
Format Request ID and SKU as plain text. Select the Google Sheets OAuth credential on Look up product draft and Save listing for review.
3. Configure the model and credentials
In Setup, set spreadsheetId, the model, and your brandVoice. Add an OpenAI Header Auth credential on Draft product listing using Authorization: Bearer <OpenAI API key>. Put a separate private Header Auth credential on Receive event.
4. Send a product brief
POST requestId, sku, productName, audience, and a facts array with label and value on each item. Use the supplied test payloads to check the brief and expected copy. The webhook acknowledges receipt; the execution and spreadsheet show the result.
5. Review before publishing
Set dryRun to false in staging and send a test SKU. Compare the draft to the supplied specifications and check the Fact References column. A valid fact reference shows what the draft cites; the editor still checks whether the wording accurately reflects it.
Use a new request ID for a new revision and process events for the same ID serially. Copy approved text to the product catalog only after editorial review.
Related automations
Use the Campaign Image & Caption System for the matching campaign visual, and the Source-Based Checklist System for a related educational asset. The Article-to-Social Draft System handles channel copy from approved articles. Read the Content Publishing & Newsletter Intelligence blueprint for the wider content process.