How it works
Jobs are the backbone of enrichment tracking. When you select products and click Start Enrichment, Cernel creates a job that processes each product with the AI agents linked to your selected attributes. Jobs run in the background, so you can continue working while content generates. The Dashboard is your command center for jobs. It shows active, completed, and failed jobs with progress indicators, product thumbnails, and attribute badges.Why you would use this
Never lose track of enrichment progress
See at a glance how many jobs are running, how far along they are, and which ones need attention.
Catch and fix issues quickly
Failed jobs show clear error indicators. Drill into specific products to see what went wrong and take action.
Running enrichment
Select a category and products
In the sidebar under Catalog, click on a category to view its products. Use the checkboxes to choose which products to enrich, or use the header checkbox to select all visible products.
Choose attributes and start
Click Enrich Products. In the enrichment modal:
- Review the Available Attributes (only attributes with linked agents appear)
- Check the attributes you want to generate (use the search box to find specific ones)
- Review the enabled Languages for your workspace
- Click Start Enrichment
The attribute count shown (e.g., “Available Attributes (5)”) only includes attributes that have an AI agent linked. If you’re missing an expected attribute, check the category’s attribute configuration.
The Dashboard
The Dashboard shows your enrichment jobs in a filterable, scrollable list. Each job appears as a card with:- Job title - The type and scope (e.g., “Product Enrichment | 24 products”)
- Status badge - The current state of the job
- Progress indicator - A circular progress bar showing percentage complete
- Product thumbnails - Preview images of the first products in the job
- Attribute badges - Which attributes are being generated
- Source - Whether the job was started manually, by an automation, or by the system
- Timestamp - When the job was created
Job statuses
| Status | Meaning |
|---|---|
| Pending | Job has been created and is waiting to be picked up |
| Queued | Job is queued in the processing pipeline |
| Running | AI is actively generating content for products |
| Completed | All products processed successfully |
| Awaiting Approval | Content generated but needs approval before syncing |
| Failed | One or more products encountered errors |
Reviewing job results
Open the job
Click on a completed job card to open the review view. You’ll see a table of products processed in this job with their status and a score showing how many attributes were filled.
Review individual products
Click Review on any product row to open the product drawer. This shows:
- Product info - Name, images, and metadata on the left
- Generated values - AI-generated attribute values in the center, each with a source badge
- Review status - Whether the product is awaiting approval or already approved
Navigate between products
Use the navigation dots at the top of the drawer to move between products in the job. Each dot shows whether the product has been reviewed (green) or is still pending (gray).
Once you’ve reviewed all products, approved content is ready to sync to your connected integrations.
Understanding value sources
Every attribute value carries a source so you can tell where the data came from. In the product table, hover over an attribute value to open its details popover. The source appears there alongside the value, with a label and icon:| Source | Icon | Meaning |
|---|---|---|
| AI Enriched | Sparkle | Generated by an AI agent during enrichment |
| Integration | Plug | Imported from a connected integration like Shopify |
| Manual Input | User | Entered or edited manually by a user. When a teammate edited the value, their email is shown below. |
Advanced configuration
Filtering and searching jobs
Filtering and searching jobs
The Dashboard supports filtering by date range, status, and search terms. Use the tabs to switch between Recent jobs and All active jobs. The search box lets you find specific jobs by name or product.
Job scores and quality tracking
Job scores and quality tracking
The score column in the job table shows the ratio of attributes successfully filled by AI versus the total number of attributes. This gives you a quick quality indicator:
- Green (80%+) - Most attributes filled successfully
- Yellow (50-79%) - Some attributes missing, worth investigating
- Red (below 50%) - Significant issues, check agent configuration
Multi-language jobs
Multi-language jobs
If your organization has multiple languages enabled, jobs process content for each configured language. You can filter the job table by language and site to focus on specific locale results.
Frequently asked questions
Why did my enrichment job fail?
Why did my enrichment job fail?
Check the job card on the Dashboard for a status indicator. Common causes:
- Agent configuration issue: the linked agent’s prompt may be empty or invalid
- Missing dependencies: a required attribute dependency isn’t enriched yet
- API error: a temporary issue with the AI provider
Can I re-run a failed job?
Can I re-run a failed job?
Not directly. Instead, go back to the product table, select the products that failed, and start a new enrichment. Check the agent configuration first to fix whatever caused the failure.
How do I find products that were deleted after enrichment?
How do I find products that were deleted after enrichment?
Deleted products still appear in the job review with a banner indicating the product has been removed from your store. The generated values are preserved for reference but can no longer be synced.
What does 'Awaiting Approval' mean?
What does 'Awaiting Approval' mean?
If you have Approve Before Push enabled in Settings > Platform, generated content must be explicitly approved before it syncs to your connected integrations. Products in “Awaiting Approval” status have generated content that hasn’t been approved yet.
Can I enrich products in multiple languages?
Can I enrich products in multiple languages?
Yes. Cernel supports multi-language enrichment. The enrichment modal shows your enabled languages, and AI generates content in each configured language. You can manage languages in Settings > Languages.
How do I enrich only products that are missing content?
How do I enrich only products that are missing content?
Use the product table’s filtering to find products with empty attribute values. Select those products and run enrichment on just the missing attributes. The filter bar lets you filter by attribute status and other product properties.
How long does enrichment take?
How long does enrichment take?
Most products finish in under a minute. Text attributes are the quickest, while attributes that generate images or pull in external data can take a few minutes per product.Adding more attributes does not make enrichment slower. Cernel works on all selected attributes for a product at the same time, so the total wait is only as long as the slowest one.Small batches typically complete in seconds. Larger runs across hundreds of products may take several minutes. If you have multiple jobs running at once, they may take a little longer as Cernel shares capacity fairly across your workspace.
How long are jobs kept in the Dashboard?
How long are jobs kept in the Dashboard?
Jobs remain visible on the Dashboard and can be filtered and searched. Recent jobs appear on the main view, and you can use View all activity to see your full job history.
What’s next
AI Agents
Create and refine agents to improve the quality of your enrichment output.
Automations
Set up automatic enrichment for new products so you don’t have to trigger jobs manually.