Skip to main content
Attributes are the data fields that AI fills in for your products: descriptions, meta titles, materials, colors, and more. You configure attributes on categories in your Cernel Taxonomy, link AI agents to them, and Cernel generates the values at scale. Seven attribute types cover everything from plain text to structured selections to images, including a Picker that selects the best value from a set of candidates.

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

Instead of deciding case-by-case what content each product should have, configure it once at the category level. Every product in that category automatically has the right fields.

Match the right content type to the job

Use Text for meta titles, HTML for rich descriptions, Single Select for gender classification, Multi Select for materials. Each type has specialized configuration for accurate AI output.

The seven attribute types

Plain text content without formatting. Best for short-to-medium content like product descriptions, meta titles, meta descriptions, and search keywords.Configuration: Prompt instructions, the AI provider that powers the agent (Google, OpenAI, or Anthropic), and optional agent dependencies on other attributes.
Rich formatted content with HTML markup, including headings, paragraphs, lists, and bold text. Best for long-form descriptions, size guides, and care instructions that need visual structure.Configuration: Prompt instructions, including the structure the AI should produce (headings, paragraphs, lists), the AI provider that powers the agent, and optional agent dependencies on other attributes.
One value chosen from a predefined list of classification options. Best for classifications like Gender (Male / Female / Unisex), Season (Spring / Summer / Autumn / Winter), or Age Group (Adult / Kids).Configuration: Define the classification options, write prompt instructions, and optionally turn on Force classification so the AI always picks an option even when evidence is limited (rather than leaving the field empty).
Multiple values chosen from a predefined list of classification options. Best for attributes where products can carry several values, like Materials (Cotton, Polyester, Elastane) or Features (Waterproof, Breathable, Lightweight).Configuration: Define the classification options, write prompt instructions, and optionally turn on Force classification. Classification options can be auto-translated into your enabled languages.
Data the agent finds on the web, rather than generated purely from the product’s existing fields. External Data operates in one of two modes, chosen on the agent’s page in the Agent Sandbox, under Advanced Settings > Search Configuration > What should the agent find?:
  • 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.
Configuration: Search sources (Google queries, AI Search prompt), optional site filtering (exclude or allow specific domains), and product matching criteria (GTIN, SKU, EAN, etc.) so results are tied to the right product. See AI Agents for the full set-up walkthrough.
Image content generated or sourced by AI. Best for product lifestyle images, styled photography, or any visual content you’d otherwise need a photographer for.Configuration: Prompt instructions describing the shot, plus image settings like aspect ratio, resolution, file format, and model behavior (Precise / Balanced / Creative). Preview and iterate on results in the agent sandbox before you save.
One or more values selected from a set of candidates, rather than generated. Best when the right answer already exists among several choices: the cleanest packshot out of all product images, the strongest tagline, or a few look-alike products from your catalog.Configuration: A search prompt that lists the candidates (optionally with Data access to your Products or Data Sources), a Strategy (AI ranks them against a rubric you write, or Random pick), and the output: Single value or Multiple values, how many to pick, and Image or Text candidates. Picker is an early-access Preview feature. See Picker agent for the full set-up walkthrough.

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.
1

Select a category in your taxonomy

In the sidebar under Catalog, expand the taxonomy tree and click the category where you want to add the attribute. The attribute will apply here and, automatically, to every subcategory beneath it.
The sidebar taxonomy tree with a category like 'Shoes' highlighted, showing the product table for that category in the main area
2

Open the Add New Attribute dialog

Click Create Attribute above the product table to open the Add New Attribute dialog.
3

Name the attribute, or pick an existing one

Type a clear, descriptive name under Name a new attribute, like Meta Description or Materials. This name appears as a column in the product table and as an option in the enrichment modal.Or, under Use an existing attribute, search for and pick an attribute your organization already has, to add it to this category as well. Attributes already on this category are marked Already on this category.
The Add New Attribute dialog with a 'Name a new attribute' field, an 'or' divider, a searchable 'Use an existing attribute' list, and Cancel, Create attribute, and Set up agent buttons

The Add New Attribute dialog

Name attributes by what the content is, not how it’s used. “Meta Description” is clearer than “SEO Text”, and “Materials” is clearer than “Tag 2”. Consistent naming makes the product table easier to scan.
4

Set up the agent, or create the attribute on its own

Choose how to finish:
  • 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.
See AI Agents for the full agent creation walkthrough, including writing prompts, referencing Data Sources, setting agent dependencies, and using the sandbox to iterate.
5

Test in the sandbox and create the agent

In the sandbox, run the agent on real products so you can verify the output. Use the agent chat to adjust the prompt, run it again, and step through versions until you’re happy.When you click Create agent, the agent is created and linked to the attribute on the category, and you return to where you started. The attribute now applies to this category and all its subcategories, and it’s ready for enrichment.
Attribute and agent are set up together. Run enrichment on products in this category to generate values.

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.
1

Open Tools > Attributes and pick a taxonomy

In the sidebar under Tools, click Attributes. Use the Taxonomy picker at the top right to choose which taxonomy the page describes, and the Market picker, when your organization has more than one market, to choose which market the completeness figures are read in.
The Attributes page with the Taxonomy and Market pickers at the top right, the search field and scope filter, and a table with Attribute, Agents, Integrations, Completeness and Tracked columns
2

Read the table

Each row is one attribute:
  • 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.
Click the Attribute, Agents, or Completeness column title to sort by it.
Tracking belongs to the attribute, so turning it on or off applies in every category and taxonomy that uses it.
3

Narrow the list

Type in Search attributes to find an attribute by name. Use the scope filter beside it to show All attributes, Tracked here, Tracked elsewhere only, Tracked, not used anywhere, or Not tracked. Each option shows how many attributes it holds.
4

Open an attribute

Click a row to open the attribute’s details beside the list. The panel shows how many categories use the attribute, how many agents fill it, and how many products it reaches. Click Add a description to say what the attribute means and how it should be filled in.
  • 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.
Connected systems refer to attributes by name, so renaming an attribute breaks its integration link until the mapping is updated.

Advanced configuration

When you add an attribute to a category, it automatically applies to all subcategories beneath it:
  • 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
Place broadly useful attributes (Meta Title, Meta Description) high in the tree, and reserve deeper categories for specialized ones (Cushioning Type, Drop Height).
If a subcategory needs slightly different output for an attribute that’s already set at a parent (for example, a more technical description for Running Shoes than for Shoes overall), link a different agent to the same attribute on the subcategory. The subcategory’s agent takes precedence for products there, while the rest of the tree continues to use the parent’s agent.This is how specialization works in Cernel: you don’t override fields inside a single attribute configuration. Instead, you choose which agent generates that attribute where it matters.
For an HTML attribute, describe the structure you want in the agent’s prompt, block by block, for example “an H2 heading, one short opening paragraph, then three bullets covering fit, material, and care”. You can ask for:
  • Heading levels (H1, H2, H3)
  • Paragraphs and bold text
  • Bullet and numbered lists
  • Line breaks
Run the agent on real products in the Agent Sandbox to check the formatting before you save, so it stays consistent across the catalog.
On the agent’s page in the Agent Sandbox, settings let you tune how the AI behaves when generating this attribute:
  • 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
These settings are configured on the agent, so they apply wherever that agent is linked.
For External Data attributes, the agent’s Advanced Settings tab in the Agent Sandbox holds the Search Configuration that drives the web search:
  • 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
The same configuration powers both Text data and Product images modes; only the extraction target changes. See AI Agents for the end-to-end setup.
Each attribute can be mapped to fields in your connected integrations. In the Integrations section of the configuration modal, you can:
  • View existing import and export mappings
  • Add new mappings to Shopify fields or metafields
  • Configure bidirectional sync behavior
This determines how enriched values flow back to your store.
For Single Select and Multi Select attributes, the allowed options can be translated into your enabled languages. Cernel shows translation status for each option and warns if any are missing. You can auto-translate options or enter translations manually.
Removing an attribute from a category also removes it from all subcategories beneath it. Previously generated values for products in those categories will be lost.

Frequently asked questions

Text produces plain, unformatted content, ideal for meta titles, short descriptions, and fields where HTML isn’t supported. HTML produces structured content with headings, paragraphs, and lists, ideal for long-form descriptions, product pages, and any field that renders HTML.To control the structure of HTML output, describe the blocks you want in the agent’s prompt and check the result in the Agent Sandbox.
The most common cause is that the attribute has no AI agent linked. This happens when an attribute was added with Create attribute (without setting up an agent) and not revisited. Open the attribute, verify an agent is assigned, and re-run enrichment.
Yes. If two categories at the same level both need a “Description” attribute, you can create it on each one. However, if the categories share a parent, it’s more efficient to add the attribute to the parent, and it will automatically apply to both.
In the product table, click the attribute’s column header to open its menu. When the attribute is set on a category higher up, the menu reads Inherited from: [Category Name], and its bottom section shows Set on [Category Name] with a Go there link to that category. For the full picture, open the attribute on Tools > Attributes: the Agents by category tab lists every category that uses it and marks where it is set.
Attributes set at a parent category automatically apply to all subcategories, so an attribute that a parent category adds can only be removed on that parent. In the product table, open the attribute’s column menu: when the attribute is set higher up, the menu shows Set on [Category Name] with a Go there link to that category, and Remove Attribute is unavailable. Follow the link and remove the attribute there, which removes it from every subcategory beneath it.If the subcategory has its own agent for the attribute, you can still click Unlink Agent on the subcategory, because that agent belongs to it.
Yes. Search demand recommends new attributes based on what shoppers search for. A recommendation such as Add Heel height to Boots lists the options shoppers look for and the monthly searches behind them. Open it and click Create attribute to add the attribute to that category with those options. You can still change the options before the agent runs. The Dashboard’s Recommendations widget shows the categories where open recommendations are worth the most.
When Force classification is on, the AI must always pick one of your classification options, even when evidence is limited. When it’s off, the AI can leave a product unclassified if it isn’t confident. Turn it on for attributes where every product must have a value (like Gender); leave it off when it’s acceptable for some products to stay empty rather than get a guess.

What’s next

AI Agents

Create the agents that generate values for your attributes.

Cernel Taxonomy

Set up your category structure to organize where attributes apply.

Completeness Score

See how filled each category is, measured against the attributes you track.

Search demand

Find the attributes and options shoppers search for that your catalog does not have yet.