Overview
The Unified AI Configurations feature introduces a centralized location for managing all AI-related attribute configuration settings in Akeneo. This includes prompt-based enrichment, asset generation, and translation customization previously configured at the attribute or family level.
By consolidating AI settings into one dedicated area, users benefit from a streamlined, scalable, and more maintainable configuration experience.
Access the page via:
Settings → AI Configurations
Configuration Structure
The new AI configurations page enables users to define reusable configurations that can be applied via the Rules Engine or manually from the Product Edit Form. These can be for all attributes or specific to one attribute, as defined by you in the configuration.
Each configuration includes:
- General Information
- A label and code for identification, and the status (enabled/disabled).
- Target & Source
- Select a specific attribute (or apply to all)
- Define which attribute values should be used for content generation.
(Note: This does not apply to translations)
- PX Insights User Reviews (Optional)
- Automatically includes relevant customer review data if PX Insights is enabled.
(Contact your CSM for more details)
- Automatically includes relevant customer review data if PX Insights is enabled.
- Assets (Optional)
- You can include assets to be considered for your configuration; you can also choose specifically which asset collections to consider.
- Instruction Prompt
- Choose a predefined prompt or define your own custom instruction.
Example of AI configuration page

Example Configurations
1. SEO Metadata Generation
Example Configuration:
- Label: SEO Meta Generator
-
Code:
seo_meta_generator
-
Target Attribute:
seo_metadescription
-
Context Attributes:
product_name
,short_description
- Assets: Not included
- PX Insights: Enabled
- Prompt:
You are an expert SEO copywriter. Using the selected attributes' values, generate a SEO-optimized meta description that:
• Does not exceed 155 characters (including spaces)
• Naturally incorporates the primary keywords
• Ends with a clear call to action
Return only the meta description text.
2. Data Quality Audit
Example Configuration:
- Label: Data Quality Audit
-
Code:
data_quality_audit
- Target Attributes: All
- Assets: Included
- PX Insights: Disabled
- Prompt:
You are a PIM data quality specialist. Analyze all attribute values and assets for each product record. Identify:
1. Missing or empty required fields
2. Format inconsistencies (currency mismatches, incorrect date formats)
3. Logical clashes (e.g. weight greater than dimensions)
4. Discrepancies between assets and attribute values
5. Detection of anomalous or outlier values (e.g., values far outside expected ranges, like a product weight in the hundreds of kilograms or a price of $0.01)
For each issue, provide a bullet list item with:
– The attribute or asset name
– A brief description of the problem
– A recommended corrective action
3. Tone-Controlled Translation
Example Configuration:
- Label: Brand Tone Translation
-
Code:
brand_tone_translation
- Target Attributes: All localizable text fields
- Assets: Not included
- PX Insights: Disabled
- Prompt:
You are a professional translator and brand voice custodian. Translate these fields using a friendly yet professional tone.
4. Set simple or multi-select values based on Asset
Example Configuration:
- Label: Set Color Scheme /w Asset for Shirt Family
-
Code:
set_color_scheme_w_asset_for_shirt_family
- Target Attributes: color (simple select)
- Assets: Packshot
- PX Insights: Disabled
- Prompt:
Assess the images provided for the product and return the base color of the shirt. Do not include small effects or patterns. Just the main color. Do not consider the background.
List of options are:
- red
- green
- blue
...
Prompt Guidelines for Generating Product Content with AI
When creating product content using AI models like ChatGPT, it’s important to provide clear and detailed instructions to ensure the generated descriptions align with your goals. Follow these guidelines to craft effective prompts that will produce precise, engaging, and high-quality product content.
1. Identify Key Features
List the essential features of the product, such as specifications, benefits, and unique selling points (USPs). Highlight what makes the product stand out compared to similar items in the market.
2. Specify the Target Audience
Consider who will be reading the product description. Tailor your prompt to resonate with your target audience's needs, interests, and preferences to create relevant content.
3. Choose the Tone and Voice
Define the tone and voice of the description. This can range from formal to informal, enthusiastic to neutral, and can include voices like professional, friendly, or whimsical. Being specific about the tone and voice helps maintain consistency in your product content.
4. Provide Context
Offer context about the content’s purpose and intended use. This helps ensure that the AI-generated content aligns with the overall goals and objectives of your project.
Note for translations: Avoid specifying source or target languages in the prompt. These settings can be configured through the Product Edit Form or Rules Engine.
5. Include Relevant Technical Specifications
If applicable, provide important technical details like dimensions, material, and compatibility. These are especially important for tech products, appliances, and gadgets to ensure accurate descriptions.
6. Mention Constraints or Special Instructions
Outline any specific constraints or requirements for the description. For example, if certain phrases, keywords, or compliance guidelines need to be included, specify them clearly in the prompt.
Character Limit Reminder: AI models focus on clarity over strict adherence to character limits. If you define a character limit, ensure that the model's output is reviewed and adjusted to meet your requirements.
7. Request Examples or Comparisons
If necessary, ask the AI to include comparisons or examples to make the product description more relatable. Comparing the product to familiar items or scenarios can help customers understand its value more easily.
8. Clarify the Purpose of the Content
Specify where the generated content will be used, whether for an online store, catalog, or marketing material. This will help shape the content to best suit the intended platform or audience.
9. Review and Refine the Prompt
Before submitting your prompt, proofread it to ensure clarity and completeness. You can test your prompt with several products in the Product Edit Form before automating it through the Rules Engine.
Example Prompt:
Product: Portable, rechargeable hand warmer "WarmPal"
Target Audience: Outdoor enthusiasts and commuters in cold climates
Tone: Friendly and informative
Voice: Casual, yet knowledgeable
Key Features:
- Compact design
- 12-hour battery life
- Fast-charging capability
- Eco-friendly materials
- Suitable for hiking, commuting, and winter outdoor activities
Technical Specifications:
- Dimensions: 3x2 inches
- Weight: 4 ounces
- Material: Recycled plastic
Special Instructions: Avoid technical jargon and make the description accessible to non-experts.
By following these guidelines and using the provided example as a template, you can create detailed and effective prompts to generate product content that aligns with your goals and resonates with your target audience.
Execution Options
1. Manual Execution via Product Edit Form
- Navigate to a product in the grid
- Locate the Ask AI button next to the target attribute
- Select Generate from configuration
- Choose the desired AI configuration
- The generated value will be populated immediately in the interface.

2. Automated Execution via Rules Engine
- Go to Settings → Rules
- Create or edit a rule
- Define product conditions as needed
- Add an action: Generate attribute value with AI
- Select the appropriate AI configuration from the list

Please note that the Action: GENERATE FROM ASSET attribute value with AI will no longer be available.
Limits & Considerations
A maximum of 200 AI configurations can be created per environment.
Family-level prompts remain active and will still be applied during execution if configured. These are not yet migrated to the unified configuration page.
To ensure optimal performance and reliability, the AI enrichment features have a few important limitations:
Supported Asset Types
The following file types are supported for asset-based AI generation:
- Images: JPG, JPEG, PNG, WEBP, TIFF, and single-frame GIFs
- Documents: PDF
Asset Limits per Product
Each product can include:
- Up to 5 images (maximum 20MB each)
- 1 PDF (maximum 50MB, first 20 pages analyzed)
Note: Larger files or additional assets beyond these limits will be skipped during processing.
Asset Collections
Only assets stored in collections that include a “main media” attribute are supported.
Processing Order
When multiple assets are available, the AI will prioritize the first images and/or PDF found in the selected asset collections.
Attribute Option Limit
For select-type attributes (simple or multi-select) used as AI outputs:
- A maximum of 500 attribute options are supported
- Any options beyond this limit will be ignored during generation
- This limit is imposed by prompt size constraints from our AI provider.
Fair Usage and Billing
There are currently no hard usage limits, but we plan to introduce customer-specific usage limits in the future to ensure fair access for all users.
Data Privacy and Security
All data is processed through OpenAI’s Enterprise API:
- Your data is not used to train AI models
- No data is stored after processing
- All data is transmitted securely over encrypted channels
Best Practices & Troubleshooting
- Use high-quality, relevant assets for better generation results
- Refine prompts to clarify tone, focus, or format
- Review all AI-generated content before publishing
- Check permissions and feature flags if you can’t access a feature
- If errors occur, try simplifying the prompt or reducing the number/size of assets
Security Overview
Akeneo takes your data security and privacy seriously. All product enrichment, whether generated from attributes, from assets (images, PDFs), or translations, is governed by robust security standards and privacy controls. We use OpenAI Enterprise and Google Gemini Enterprise, ensuring that the data we provide isn't utilized in model training. This data flows exclusively within their servers, returning directly to us without storage or reuse. We share only precise information with OpenAI to ensure that we generate accurate content tailored to your requirements.
AI models used
We are currently using OpenAI's ChatGPT models:
Use Case | Model |
---|---|
Text generation | GPT-4.1-mini |
Translation | GPT-4.1-mini |
Rephrasing | GPT-4.1-mini |
Image analysis | GPT-4.1-mini |
Information shared with our AI provider
For content generation
- Product name: the value of the attribute used as a label
- Locale: the language of the generated content
- Values: the values of the product in the selected attributes to take into account
- Prompt: whether it is a pre-defined Akeneo prompt or your custom one that you have defined
For content translation
- Source locale
- Target locale
- Value to translate
- Prompt: your custom one that you have defined
For content rephrasing
- Value to rephrase
- Rephrase type
We don't share the metadata of our clients (as clients' names for example) with OpenAI. Some clients might want to add these kind of infos in their prompt, but we can guarantee that we are not adding these kind of informations on your behalf.
Additional Security Measures
- Data is transmitted over secure, encrypted channels.
- No personal data or credentials are ever sent to the AI service unless explicitly included by the user.
- You have full control over which attributes, assets, and prompts are used and shared.
- Feature flags and permissions allow granular control of access and usage per user and per customer.
Compliance & Recommendations
- Always review AI-generated content before publishing for accuracy, compliance with company policy, and regulatory standards. You can use Workflows to do so.
- Do not include confidential or sensitive information in prompts or attribute values unless necessary and reviewed.
- If required, consult your legal or data protection team to ensure usage is in line with your organization’s privacy and data governance policies.
Our AI features are designed to help you work faster and more efficiently, but they rely on clear inputs (or "prompts") to produce the best results. Sometimes, if the instructions are too broad, vague, or missing product context, the output might not meet your expectations.
We’re here to help you get the most out of AI. If things don’t look right, it’s not your fault, and it’s not magic either. Think of it like working with a new colleague: the clearer you are, the better they can help.
We’re constantly improving the experience and would love your feedback. In the meantime, check out our Prompting Guide to help you write better prompts and save time.
Frequently Asked Questions (FAQ)
1. How can I generate content using both attributes and assets?
You can create a configuration that combines product attributes and assets. When defining the configuration, select the relevant attributes and asset collections. The AI will use both types of data to generate the content.
2. Can I use AI enrichment directly in the Product Edit Form?
Yes. Once a configuration is created and the appropriate permissions are enabled, you can click the "Ask AI" button next to supported attributes in the Product Edit Form and select a configuration to generate content.
3. What are the limits for asset-based enrichment?
- Up to 5 images (20MB each)
- 1 PDF (50MB max, first 20 pages analyzed)
- Supported types: JPG, PNG, WEBP, TIFF, single-frame GIF, and PDF
- Only assets from collections with a "main media" attribute are supported
4. Why are some attributes or actions locked when creating rules?
If you’re seeing locked fields in the Rules Engine, it’s likely that the target attribute hasn’t been enabled for AI enrichment. Go to Settings → Attributes, select the attribute, and enable it under the “Generative AI” tab.
5. Is there a limit to the number of AI configurations I can create?
Yes, each environment supports up to 200 AI configurations. You can reuse and update configurations as needed.
6. What are the limits for select-type attributes used with AI?
When generating values for Simple Select or Multi-Select attributes:
- A maximum of 500 options are supported per attribute
- Any additional options beyond the first 500 will be ignored due to prompt size limitations from the AI provider
7. How long does AI enrichment take to run?
Performance depends on several factors, including:
- Number of products targeted
- Number of AI actions per rule
- Number of locales involved
- As a reference, processing 20,000 products with 5 assets each may take up to 24 hours.
8. Can I still use family-level prompts?
Yes. Existing family-level prompts will still apply during AI generation, even though they are not managed through the new configuration page.
9. Is my data secure when using Akeneo AI features?
Yes. Akeneo uses OpenAI’s Enterprise API and Google Gemini Enterprise to power AI features. Your data is:
- Never used for training
- Not stored after processing
- Not transmitted securely over encrypted channels
10. What information is shared with the AI provider?
Action | Data Shared |
---|---|
Content Generation | Product name, selected attribute values, prompt, locale |
Translation | Source & target locales, value, prompt |
Rephrasing | Value to rephrase, type of rephrasing |
We do not send customer-identifying metadata (like your company name) unless explicitly included by you in the prompt.
11. Are there usage limits?
Currently, usage is governed by your billing plan. Akeneo monitors AI usage for cost management and fairness. We will be introducing customer-specific usage limits in the future.
12. How can I write better prompts for AI content?
Effective prompts are key to quality results. Include:
- Key product features
- Target audience
- Tone and voice (e.g., professional, playful)
- Technical specs (if needed)
- Clear formatting or character constraints
- You can test prompts in the Product Edit Form before automating them in a rule.
13. Can AI-generated content be reviewed before it goes live?
Yes. You can manually review content in the Product Edit Form or use Workflows to ensure content accuracy, compliance, and brand consistency before publishing.