Generate JSON-LD Structured Data
Describe your content and ChatGPT builds valid JSON-LD for a product, article or local business that you can embed straight away.
Last updated: July 2026 · Collective Brain
Good for
- Mark up product pages with price, availability and ratings for rich results
- Add Article schema with author, date and image to blog posts
- Structure your business location cleanly as LocalBusiness data
The prompt
You are a technical SEO expert focused on structured data and the schema.org standard.
Context:
- Schema type: [product, article or local business]
- Content data: [all relevant details, e.g. name, description, price, currency, availability, address, opening hours, author, date, image URL]
- Page language and URL: [e.g. English, https://your-domain.com/page]
Task:
Create valid JSON-LD markup following schema.org for the type above. Use only the fields I have provided data for and do not invent values. Apply correct data types (prices as numbers, dates in ISO 8601 format) and the right nested objects, such as offers, aggregateRating, address or openingHoursSpecification. Keep the syntax clean and the JSON valid.
Output format:
1. The finished JSON-LD in a code block, wrapped in <script type="application/ld+json">.
2. A short list of the fields you used.
3. A list of recommended fields I should still add for a complete rich result, with a note on why they matter.
4. The Google rich result type this markup can trigger.
Ask me for any required fields the chosen type needs instead of guessing them.Replace the bracketed placeholders with your own details.
Frequently asked
Which schema types does this prompt cover?
It is built for the three most common cases: Product with offers and aggregateRating, Article with author and date, and LocalBusiness with address and opening hours. You can also change the schema type placeholder to related types like Recipe, Event or FAQPage.
Is the generated markup guaranteed to be error-free?
No. ChatGPT produces very clean JSON-LD, but it can misname fields or use outdated properties. Always run the output through the Google Rich Results Test and the schema.org Schema Markup Validator before you publish it.
Related
Rather have it done?
Prompts are a start.
Results are our job.
When the prompt should turn into real work that holds up consistently across every channel, we take over. Start free, finish professionally.