How it works
An AI agent is a configured AI with a specific job: generate product descriptions, extract materials from images, classify products by gender, create meta titles, whatever content your products need. You build an agent by defining its prompt (the instructions the AI follows), selecting the attribute type it produces (Text, HTML, Single Select, Multi Select, External Data, or Media), and optionally referencing Data Sources for brand guidelines and context. Once created, you link the agent to an attribute on one or more categories in your Cernel Taxonomy. The agent then generates content for every product in those categories when you run enrichment. The key concept: agents are independent from categories. You create them once and reuse them wherever they’re needed. Change an agent’s prompt, and every category using that agent picks up the update.Why you would use this
Write instructions once, generate everywhere
Keep your brand voice consistent
Specialize by product type
Iterate without re-doing work
Planning your agents
Before creating agents, think about what content your products need. A typical setup includes:- A product description agent (Text or HTML) for your main product copy
- A meta title and meta description agent (Text) for SEO
- A materials or features agent (Multi Select) for structured attributes
- Specialized agents for specific product types (e.g., technical specs for electronics)
Creating an agent
Open the Agents page

The Agents page: every agent with its type, linked categories, and creation date
Click Create Agent

The start screen of a new agent: describe what it should do, optionally pin its type, or pick one of the other ways to begin
Choose how to start
- Describe your intent (recommended): type a short description of what the agent should do, for example “Write a 150-word product description that’s professional but approachable, focusing on materials and fit”, and click Generate agent. The chat drafts a full agent with the right structure, references, and instructions.
- Use a template: start from a ready-made agent in the template library. See Quick start with agent templates below.
- Copy from existing: create a new agent that starts with the settings of one you already have.
- Manual input: enter the name, type, and prompt yourself, with no AI assistance.
- Text: Plain text like product descriptions and meta titles
- HTML: Rich formatted content with HTML markup
- Single Select: Choose one value from a list (e.g., Gender: Male / Female / Unisex)
- Multi Select: Choose multiple values from a list (e.g., Materials: Cotton, Polyester)
- External Data: Data fetched from an external source (e.g., GTIN matching)
- Media: Image content generated or sourced by AI
- Picker (Preview): Instead of generating a value, it selects the best one, or several, from a set of candidates. See Picker agent below.
Configure the prompt
- What to generate: the exact type of content (e.g., “a 150-word product description”)
- Tone and style: your brand voice (e.g., “professional but approachable”)
- What to include: specific details the output must cover
- What to avoid: content or phrasing to exclude
/ in the prompt editor to reference the product’s own attributes and data directly in your instructions. The reference menu lets you insert:- Product data: all of the product’s attributes at once (All product data), or any single attribute. Every attribute is listed under the Product attributes caption inside Product data, the current category’s own attributes first (with their type shown), then the rest of your organization’s attributes, including values other agents have already generated on the same product.
- Product title, Product images, and GTIN: shortcuts to the most-used product fields.
- Product identifiers: a specific identifier such as SKU, GTIN, or MPN.
- Product defining attributes: the values that make this product a distinct variant, such as its Size or Color, resolved from wherever the variant axis was introduced in the product hierarchy.
- Data Sources: entries from your organization’s context library (brand voice, product rules, compliance guidelines).

- Data: All, Base, or Enriched. Base data keeps an attribute only while its value comes from an integration or a CSV import. Once an agent or a person changes the value, the attribute counts as Enriched data. Pick Base when the agent should work from your supplier data only, without reading values other agents have written.
- Attributes: Leave out the attributes you pick, or Only include the attributes you pick. Use this to keep attributes out of the agent’s input when they would distract it or don’t belong in what it writes.
- Include images: also sends image values to the model as images. It’s off by default, since images cost more and take longer.
- Variants: turn on Fill in from variants to fill the product’s empty values from the first variant that has one. Attributes that only the variants have aren’t added this way. To use one, add it on its own with
/and turn the option on for that pill.
/ followed by a space (as in “short / no emojis”) is treated as punctuation and doesn’t open the menu. If a search matches nothing, pressing Enter closes the menu and adds a new line as usual./ menu. Find a specific identifier under Product Identifiers instead. Prompts that already reference External Data or ID keep their pills and keep working.Data Sources > Models > ToV), so you can jump straight back to a parent level when you’ve dug too deep. Search inside the picker is space-tolerant: type Specifications type 1 and it matches entries named specifications_type_1.
Test in the sandbox and refine
@ to point out exactly what needs improving. The chat updates your prompt based on your feedback. Click Run test to see the change on the same products, or ask the chat to run the test for you and explain the results.Each refinement creates a new version of your prompt. Open the Changes tab to see what each change did, and use Restore this version on an earlier one to go back to it if a change didn’t improve things. Keep iterating: adjust the prompt through chat, review the new results, and repeat until you’re happy. If the agent should check its own output before it reaches your catalog, add Review Steps (an add-on module, not enabled by default) before you save. See Agent Sandbox for the full reference, including @-mentions, the detail drawer, and per-type behavior.Save the agent
Linking an agent to a category
Navigate to a category
Open the attribute settings
Link the agent
Running enrichment
Select products to enrich
Choose attributes and start enrichment
Monitor the job

Job details showing products with their enrichment status and scores
Review and approve results

The review interface: inspect AI reasoning, view source data, and approve results
Advanced configuration
Quick start with agent templates
Quick start with agent templates
- On the Agents page, click Create Agent to open the Agent Sandbox.
- Under Other options, click Use a template.
- Browse the library: search by name, or filter by agent type. Where the library has them, a Popular view lists a handful of hand-picked templates first.
- Pick a template and click Use template. The sandbox opens with the template’s configuration filled in, so you can test it on your products straight away.
- Give the agent a name, review the prompt, and click Create agent.
- Connect your product source (Shopify, CSV, Feed, or API)
- Add the attributes your categories need
- Create agents from templates for each attribute
- Test on 5-10 products and review quality
- Customize prompts - add your brand voice via Data Sources
- Scale up - enrich your full catalog or set up Automations
Agent reasoning
Agent reasoning
Dependencies between agents
Dependencies between agents
AI provider and model behavior
AI provider and model behavior
Enrich variants from their own data only
Enrich variants from their own data only
Require or skip review for one attribute
Require or skip review for one attribute
- Require review: new values for this attribute wait in Review until someone approves them.
- Approve automatically: new values for this attribute skip review and are sent to your connected site.
External Data agents: Classic vs Agentic mode
External Data agents: Classic vs Agentic mode
- Block these domains: results from these domains are excluded
- Restrict to these domains: when non-empty, only these domains are considered
- Match by [identifier]: pick a product identifier such as SKU, GTIN, or EAN. The agent requires that identifier to appear in the result to count as a match. Highest accuracy when you have identifiers in your catalog.
- Match by Broad search: match on the product’s title and details instead. More flexible, but more likely to surface inaccurate results.
- Custom match criteria (optional): add extra words or codes a result must contain. Leave blank to match on the title automatically.
/ to insert references to product data, Data Sources, or other attribute values, exactly like the prompt step for a Text agent.External Image Enrichment
External Image Enrichment
- Search: The agent runs web searches using queries you define (e.g., product name + brand + “product photo”)
- Extract: Cernel visits the search result pages and extracts images, guided by your extraction prompt
- Output: A deduplicated list of images is returned as the attribute value, ready for review
- Create an agent with External Data as the attribute type, then switch to Image mode
- Define search queries that reference product data (e.g.,
{product_name} {brand} product photo) - Write an extraction prompt that tells the AI what images to look for (e.g., “Extract high-resolution product photos, ignore thumbnails and navigation images”)
- Link the agent to an External Data attribute on your taxonomy and run enrichment
Media agents: image output, alt text, and file names
Media agents: image output, alt text, and file names

The Advanced Settings tab of a Media agent: image output settings plus Alt Text and File Name instructions
- Google: Nano Banana 2.1. This is the default for new Media agents.
- OpenAI: GPT Image 2.6 Sunburst.

The Image generation model cards on a Media agent's Advanced Settings tab, with Model Behavior below
- Aspect Ratio: the shape of the generated image (for example,
9:16for a tall product shot). - Resolution: the output image quality. Leave it on Default to use the model’s native output.
- File Format: the output file type: Default (model output), PNG, JPEG, or WebP.
/ to insert references to product data, Data Sources, or other attribute values, so the alt text and file name can pull in details like the product title or color automatically.Recolor a Media agent's image backgrounds
Recolor a Media agent's image backgrounds
- Background color: the solid color the background becomes, entered as a hex value (for example,
#FFFFFF). - Mode: how Cernel treats shadows behind the product:
- Replace background: best for product shots; removes shadows as well.
- Preserve shadows: best for studio shots of models; keeps the natural shadows.
- Hybrid (clean background, keep shadows): keeps only the clearest shadows near the product or model and recolors everything else to your exact color. Choose it when the background must match a precise color but you still want some depth.
- Processing engine: how firmly Cernel trims the edges around the subject:
- Standard (recommended): keeps the most natural edges; the right choice for most images.
- Alternative: trims edges more firmly. Pick this if you notice a faint halo around the product or model, though it can give harder edges around fine details like hair.

The Recolor background section in a Media agent's Advanced Settings: the Background color, Mode, and Processing engine controls
Global Prompts
Global Prompts
Per-agent language instructions
Per-agent language instructions
Picker agent
How a Picker agent works
A Picker runs as a two-phase pipeline: first it gathers candidates, then it picks from them. Phase 1: Find candidates. A search prompt lists the candidates to choose from. Reference product data with{{placeholders}} such as {{images}} or {{title}} (for example, “List all available product images: ”). By default, candidates are read straight from the prompt. You can optionally widen the net with Data access:
- Products: let the agent search your product catalog (useful for “shop-a-look” or look-alike picks). Pin a category and filters to focus the search.
- Data Sources: let the agent browse your organization’s reusable content to source candidates.
- AI ranks them: a second AI pass scores the candidates against a Rubric you write (for example, “Pick the cleanest, frontal packshot with a plain background.”). A rubric is required for this strategy.
- Random pick: skip the AI and choose at random. It’s fast, free, and reproducible: set a Seed and the same candidates always produce the same pick (handy for tests). Leave the seed blank for a fresh pick each run.
Output
In the Output section, choose what the agent produces:- Values: whether the agent selects a Single value or Multiple values.
- What it picks: whether the candidates are Images or Text.
- All that fit: every candidate the agent finds is kept, in alphabetical order. No selection step runs.
- At most N: the agent keeps up to N values, fewer when only some candidates fit, and none (saving no value) when none of them do. Choose this when a partial result is still useful.
- At least N: the agent must find at least N values. If it finds fewer, nothing is saved and the agent reports an error.
- Exactly N: the agent must find exactly N values. If it finds fewer, nothing is saved and the agent reports an error.
- Between N and M: the agent keeps between N and M values. If it finds fewer than N, nothing is saved and the agent reports an error.
What a text Picker outputs
When a Picker outputs Text and has Products data access turned on, it picks whole products from your catalog, so you can choose what each pick actually carries. An Each pick outputs setting appears with three options:- Product title (the default): every pick is the title of the product the agent chose.
- An attribute: every pick is the chosen attribute’s value on the product the agent picked. Pick the attribute with the selector that appears. Products without a value for that attribute are skipped.
- What the prompt asks for: the agent reads your search prompt to decide what to output, for example “pick a product’s material”. It falls back to the title when the prompt names nothing.
Creating a Picker agent
Choose the Picker type
Set the output
Write Phase 1: find candidates
{{placeholders}}. Turn on Data access to Products or Data Sources if you want the agent to look beyond the prompt.For a Text Picker with Products access, set Each pick outputs to control what each pick carries: the product title, a named attribute, or whatever the search prompt asks for. See What a text Picker outputs.Set Phase 2: select
Save and link it
Frequently asked questions
How do I update an agent's prompt for all categories at once?
How do I update an agent's prompt for all categories at once?
Why is the AI output not matching my brand voice?
Why is the AI output not matching my brand voice?
- Your agent prompt: make sure it includes specific style and tone instructions, not just what to generate. Open the agent, run the sandbox, and use the agent chat to tell the AI exactly what to adjust.
- Data Sources: reference a Data Source containing your brand guidelines in the prompt. Type
/in the prompt editor to insert one. - Global Prompts: check Settings > Global Prompts for any system-level instructions that might conflict with your agent’s style.
My Picker agent fails when it can't find enough candidates. How do I let it keep what it finds?
My Picker agent fails when it can't find enough candidates. How do I let it keep what it finds?
Can I use the same agent for different attribute types?
Can I use the same agent for different attribute types?
Can I duplicate an existing agent?
Can I duplicate an existing agent?
What happens if I delete an agent that's linked to categories?
What happens if I delete an agent that's linked to categories?
Can I control the alt text and file names of AI-generated images?
Can I control the alt text and file names of AI-generated images?
/ in either field. Leave a field empty to use Cernel’s default. See Media agents: image output, alt text, and file names.How many products can I enrich at once?
How many products can I enrich at once?
Can I review AI-generated content before it goes live?
Can I review AI-generated content before it goes live?
