Data Quality Best Practices

Product data quality directly affects how your items appear in ChatGPT and ultimately impacts conversion rates. This chapter consolidates ACP’s data quality requirements and recommendations.

6.1 ID Stability

Product IDs and variant IDs must remain stable throughout their entire lifecycle.

Correct: prod_earbuds_001 — always use this same ID
Wrong:   generate a new ID on every upload — loses purchase history and recommendation data

Why this matters:

ChatGPT tracks purchase history and user preferences by product ID
Changing an ID is equivalent to creating an entirely new product; all prior data is lost
ID instability degrades the product’s ranking and frequency in AI recommendations

6.2 Description Format

Provide at least one description format. Plain text is recommended:

{
  "description": {
    "format": "plain",
    "content": "Premium wireless earbuds with active noise cancellation, 30-hour battery life, and IPX5 water resistance."
  }
}

Descriptions should:

Accurately reflect the product’s actual features
Include key specifications (dimensions, weight, materials, etc.)
Avoid marketing hyperbole
Be easy for AI systems to parse and retrieve

6.3 Variant-Specific Fields

The following fields should be set independently on each Variant, not only at the Product level:

Field	Purpose	Rationale
`title`	Variant title	Distinguishes different specifications
`url`	Variant page URL	Links directly to the specific variant page
`description`	Variant description	Describes specification-specific differences
`media`	Variant images	Shows images for the corresponding color/style
`availability`	Stock status	Different variants may have different inventory
`price`	Price	Different variants may have different prices

variant_options

Use variant_options to label user-facing specification dimensions:

{
  "variant_options": [
    { "name": "Color", "value": "Midnight Black" },
    { "name": "Size", "value": "256GB" }
  ]
}

These dimensions are presented to users as selectable options in ChatGPT’s product display.

6.4 URL Conventions

Add Tracking Parameters

Include utm_medium=feed in all product URLs to track traffic originating from ACP:

https://store.example.com/products/earbuds-pro?utm_medium=feed

Use Durable Public URLs

Seller URLs must:

Be durable public URLs
Not contain expiring session tokens or temporary parameters
Remain accessible over the long term

Correct: https://store.example.com/products/earbuds-pro
Wrong:   https://store.example.com/session/abc123/products/earbuds-pro

URL Encoding

All URLs must be valid and properly encoded:

Correct: https://store.example.com/products/my%20earbuds
Wrong:   https://store.example.com/products/my earbuds

Encode spaces as %20 and handle special characters per URL encoding standards.

6.5 Prohibited Content

The following product categories must not be submitted through ACP:

Category	Description
Adult content	Pornographic or sexually explicit material
Alcohol / Tobacco / Gambling	Alcoholic beverages, nicotine products, gambling services
Weapons	Firearms, ammunition, regulated bladed weapons
Prescription drugs	Medications requiring a doctor’s prescription
Unauthorized financial services	Unlicensed financial or investment products
Illegal goods	Any products violating applicable laws
Deceptive products	False advertising, counterfeits, misleading merchandise

Submitting prohibited content may result in merchant account suspension or termination.

6.6 Data Freshness

Keep inventory and pricing data up to date:

Data Type	Recommended Update Frequency
Stock status	Real-time or hourly
Price changes	Immediately upon change
New product listings	Push via API immediately
Product delistings	Update immediately or remove in the next daily snapshot
Promotions	Create in advance; set automatic expiration

Stale inventory and pricing data leads to poor user experiences (e.g., a user attempts to purchase an out-of-stock item) and may reduce the merchant’s visibility weighting on the platform.

6.7 Image Quality Guidelines

Requirement	Details
Resolution	High-resolution with clearly visible product details
Background	Solid white or neutral background preferred
Angles	Primary image shows the product front; supplementary images show multiple angles
Format	JPEG or PNG; URLs must be publicly accessible
Consistency	Maintain a consistent style across images of the same product
No text overlays	Avoid adding promotional text on product images

{
  "media": [
    {
      "type": "image",
      "url": "https://cdn.example.com/products/earbuds-pro-front.jpg"
    },
    {
      "type": "image",
      "url": "https://cdn.example.com/products/earbuds-pro-side.jpg"
    }
  ]
}

6.8 Quality Checklist

Before submitting product data, verify each item:

Next chapter: Chapter 7: Testing and Validation — Small-batch testing, format validation, and common error troubleshooting

ACP promotions and discount configuration ACP product data testing and validation

Start

Learning Paths

Getting Started with AI Commerce

OTR Open Trust Registry

UCP Universal Commerce Protocol

ACP Agentic Commerce Protocol

MCP Model Context Protocol

SEO for the AI Era

ORBEXA Integrated Solution

Templates & Prompts

Glossary

ACP product data quality best practices

Data Quality Best Practices

6.1 ID Stability

6.2 Description Format

6.3 Variant-Specific Fields

variant_options

6.4 URL Conventions

Add Tracking Parameters

Use Durable Public URLs

URL Encoding

6.5 Prohibited Content

6.6 Data Freshness

6.7 Image Quality Guidelines

6.8 Quality Checklist

​Data Quality Best Practices

​6.1 ID Stability

​6.2 Description Format

​6.3 Variant-Specific Fields

​variant_options

​6.4 URL Conventions

​Add Tracking Parameters

​Use Durable Public URLs

​URL Encoding

​6.5 Prohibited Content

​6.6 Data Freshness

​6.7 Image Quality Guidelines

​6.8 Quality Checklist

Data Quality Best Practices

6.1 ID Stability

6.2 Description Format

6.3 Variant-Specific Fields

variant_options

6.4 URL Conventions

Add Tracking Parameters

Use Durable Public URLs

URL Encoding

6.5 Prohibited Content

6.6 Data Freshness

6.7 Image Quality Guidelines

6.8 Quality Checklist