How it works
Each attribute defines a specific piece of product data that you want AI to generate. You create an attribute on a category, choose its type, and link an AI agent that knows how to produce that content. When you run enrichment, the agent generates values for every product in that category. Attributes set at a parent category automatically apply to all subcategories beneath it. Add “Meta Description” to Apparel and every subcategory (Shoes, Tops, Accessories) gets it too. You can also add specialized attributes further down the tree that only apply to specific product types.Why you would use this
Define what data your products need
Match the right content type to the job
The seven attribute types
Text
Text
HTML
HTML
Single Select
Single Select
Multi Select
Multi Select
External Data
External Data
- Text data: The agent searches the web (Google and/or AI Search) using queries you define, then extracts textual data such as GTINs, supplier specifications, ingredients, or any other attribute you can describe. Use this when your products don’t carry the data natively and you want Cernel to source it.
- Product images: The agent uses the same search infrastructure, but targets product imagery. It follows search results and extracts relevant photos, returning a deduplicated list of images ready to review. Use this when you’re missing imagery for products and want Cernel to find real photos from the web.
Media
Media
Picker (Preview)
Picker (Preview)
Adding an attribute to a category
In Cernel, you add an attribute to a category from the Add New Attribute dialog. You either name a new attribute or reuse one your organization already has, and then set up the agent that fills it in the Agent Sandbox, or skip the agent for now. The agent you choose determines the attribute’s type (Text, HTML, Single Select, Multi Select, External Data, Media, or Picker), so you don’t have to pick a type up front.Select a category in your taxonomy

Open the Add New Attribute dialog
Name the attribute, or pick an existing one

The Add New Attribute dialog
Set up the agent, or create the attribute on its own
- Set up agent: opens the Agent Sandbox for this attribute. Describe what the AI should do, start from a template, copy an existing agent, set it up by hand, or pick Use existing agent to link an agent you’ve already built (for example, a product description agent you use across several categories). The attribute takes on the agent’s type.
- Create attribute: adds the attribute to the category without an agent, as a placeholder you can link an agent to later.
Test in the sandbox and create the agent
The Attributes page
The Attributes page, under Tools > Attributes, lists every attribute in your organization in one place: which agents fill it, which connected systems it comes from or goes to, how filled it is, and whether it is tracked in completeness. Use it to keep your attributes tidy and to decide which ones count towards the Completeness Score. The Manage attributes link in the Catalog’s Insights banner opens it too.Open Tools > Attributes and pick a taxonomy

Read the table
- Attribute: the attribute’s name, with its description underneath when it has one.
- Agents: how many agents fill the attribute in this taxonomy and across all taxonomies, for example 2 / 3 agents, or no agent yet. A count of overrides means a subcategory uses its own agent instead of the one above it.
- Integrations: whether the attribute is imported from or exported to a connected system, or not connected.
- Completeness: how filled the attribute is in this taxonomy, as a percentage and a bar, or not scored when it has not been measured there.
- Tracked: a switch that turns tracking in completeness on or off, and how many categories use the attribute in this taxonomy and across all taxonomies. A tracked attribute that no category in this taxonomy uses is marked Tracked elsewhere only, and one no category uses at all is marked Not used anywhere.
Narrow the list
Open an attribute
- Agents by category shows the categories in this taxonomy that use the attribute and which agent fills it in each. A category is marked used here where the attribute is set, inherited where it applies from a category above, and replaces the one above where a subcategory uses its own agent.
- Integrations shows the connected systems that import or export the attribute, and under which name.
Advanced configuration
How attributes apply across categories
How attributes apply across categories
- An attribute on Apparel is available on Shoes, Tops, Accessories, and every category below them
- A more specialized attribute on Running Shoes only affects Running Shoes and its children; siblings like Casual Shoes are unaffected
Customizing an attribute for a subcategory
Customizing an attribute for a subcategory
Structuring HTML output
Structuring HTML output
- Heading levels (H1, H2, H3)
- Paragraphs and bold text
- Bullet and numbered lists
- Line breaks
AI settings and behavior
AI settings and behavior
- AI provider (Text, HTML, Single Select, and Multi Select): choose Google, OpenAI, or Anthropic. Cernel chooses which of that provider’s models runs the agent.
- Model behavior (Media): choose between Precise, Balanced, and Creative to trade off consistency against variation in the generated images
- Agent dependencies: mark other attributes as required or optional inputs so one agent can build on another’s output (for example, a Meta Description agent that reads the Product Description)
- Force classification (Single Select and Multi Select): require the AI to always pick an option even when confidence is low, rather than leave the field empty
External Data: search sources and matching
External Data: search sources and matching
- Search sources: up to three Google queries plus an AI Search prompt, each of which can reference product data using
/(for example,{product_name} {brand} product photo) - Site filtering: exclude specific domains or restrict the search to an allow-list
- Product matching criteria: identifiers such as GTIN, SKU, or EAN that tie results back to the right product
Integration mapping
Integration mapping
- View existing import and export mappings
- Add new mappings to Shopify fields or metafields
- Configure bidirectional sync behavior
Translations for classification options
Translations for classification options
Frequently asked questions
What's the difference between Text and HTML?
What's the difference between Text and HTML?
Why aren't my attribute values generating?
Why aren't my attribute values generating?
Can I use the same attribute name on different categories?
Can I use the same attribute name on different categories?
How do I see which parent category an attribute comes from?
How do I see which parent category an attribute comes from?
Why can't I remove an attribute from a subcategory?
Why can't I remove an attribute from a subcategory?
Can AI recommend which attributes I should add?
Can AI recommend which attributes I should add?
What does 'Force classification' do for select attributes?
What does 'Force classification' do for select attributes?
