Skip to main content
Enrichment in Cernel happens in two steps. First, a job runs your AI agents across the products you selected and proposes new attribute values. Then, on the Review surface, you approve, edit, or reject those proposed values before they’re saved to your products and synced to your integrations. The Jobs page tracks the runs; Review is where you make the decisions.

How it works

When you select products and click Enrich Products, 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 keep working while content generates. What happens to the generated values depends on the Review toggle in the enrichment modal:
  • Review on: proposed values are held as pending and collected on the Review surface, where you approve, edit, or reject them before they go live.
  • Review off: proposed values are applied to your products automatically as soon as they’re generated, with no approval step.
The Jobs page (sidebar → Jobs) tracks every run with progress indicators, plus a search box and filters to find a past run. The Dashboard also surfaces a compact Recent jobs widget. The Review surface, reached from the Review tab at the top of the Catalog, or by opening a job from the Jobs page, is where proposed values wait for your decision.

Why you would use this

Stay in control of what goes live

Nothing is saved to your products until you approve it. Review proposed values one product at a time, or approve in bulk when you trust the output.

Understand every proposed value

For each value, see the prompt that produced it, the agent’s reasoning, the inputs it used, and where any translation came from, so you can decide with confidence.

Never lose track of enrichment progress

See at a glance how many jobs are running, how far along they are, and who started them.

Catch and fix issues quickly

Failed and skipped values are surfaced for you to dismiss, so your review queue reflects only what still needs a decision.

Running enrichment

1

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.
2

Choose attributes and start

Click Enrich Products. The Configure Enrichment modal opens:
  1. Optionally give the run a Title so it’s easy to find later on the Jobs page. Leave it blank and Cernel names the job for you from the attributes and category you picked (for example, Color from Electronics)
  2. Set the Product Scope. It opens on Include product variants, so a master product and its variants are enriched together, which is what variant-heavy catalogs usually want. Switch it to Selected products only, or to Product variants only, if you’d rather narrow the run
  3. Toggle Review on to hold generated values for approval on the Review surface before they’re saved, or off to apply them automatically. Its starting position follows your organization’s approve-before-push setting (new organizations start with it on, so first runs are held for review by default), and you can override it per run
  4. Toggle Only enrich missing fields on if you only want to fill in attributes that are currently empty (existing values won’t be overwritten). Leave it off to re-enrich all selected attributes
  5. Check the Attributes you want to generate (only attributes with a linked agent appear here, so use the search box to find specific ones)
  6. Under Language Configuration, choose what happens for each enabled language: Generate the content from scratch, Translate it from another language, or Skip it. Use Apply to all to set every language at once
  7. Click Preview to see a summary of the run, then Start Enrichment to dispatch it
The Configure Enrichment modal showing the optional Title field, the Product Scope selector, the Review and Only enrich missing fields toggles, the Attributes picker, and the Language Configuration section with Generate, Translate, and Skip options for each language
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.
To pick several attributes at once, click the first one, then hold Shift and click another: every attribute between the two is selected together. The range follows the list as shown, so if you’ve typed in the search box it covers just the matching attributes.
Use Only enrich missing fields when you’ve added a new attribute to a large catalog and want to backfill values for products that lack one, without touching anything you’ve already reviewed or hand-edited.
Each enrichment run processes up to 50,000 products in a single job. If you select more than that, only the first 50,000 are enriched in that run, and the rest are left untouched, with no error. To enrich a catalog larger than 50,000 products, split it into runs of 50,000 or fewer (see below).

Searching the product table

The search box in the toolbar above the product table finds products by title, SKU, or EAN. You don’t have to type a title exactly as it’s written: Cernel matches each word of your search against the title on its own, in any order. For example, osprey ozon finds “Osprey - Ozone 100 Kuffert”, and brown osprey backpack finds brown Osprey backpacks, so you can mix brand, product type, and color freely. Each matched word is highlighted in the product name. Results are ranked so the closest match comes first:
  1. A product whose SKU or EAN is what you typed
  2. A title that is exactly what you typed
  3. A title that contains your words in the order you typed them
  4. A title where your words appear as whole words (sort ranks a product titled “Sort” above one titled “Sortiment”)
  5. Every other match
Search for a title or for an identifier, not both at once: a search that mixes title words with a SKU, such as Skinny Jeans VI071BL, finds nothing.

Searching for a list of identifiers

To pull up a specific set of products, for example a list of SKUs from a spreadsheet or a report, paste the whole list into the search box. Separate the values with commas (1111, 2222, 3134) or paste them one per line, straight from a spreadsheet column: line breaks become commas as you paste. The table then shows every product with an identifier (SKU, EAN, GTIN or any other identifier type) that is exactly one of the values, so you can select them all and enrich, bulk edit, or export them in one go. A list search works differently from a normal search:
  • Each value must match an identifier exactly, including upper and lower case. Part of a SKU doesn’t match, and titles aren’t searched.
  • Any search that contains a comma or a line break is read as a list. A title search that includes a comma, such as Jeans, blue, finds nothing, so leave the comma out.
  • Values separated only by spaces (1111 2222) are not a list: they are searched as ordinary text.
  • One search takes up to 5,000 values.
The same list search works wherever you search for products by name or identifier, including the product picker in the Agent Sandbox. While a search or filter loads on a large catalog, the table keeps the current rows on screen and shows Searching products… until the new results arrive, which can take a few seconds.

Filtering the product list

A category can hold thousands of products, so the toolbar above the product table lets you narrow the list to exactly the set you want before you enrich. Filtering is how you build a batch, focus on products that are still missing a value, or find everything a particular integration populated. Open Filter in the toolbar above the table, then click Add filter to build a condition. Each condition reads like a sentence, for example Where Color has no data. You can filter on:
  • Product attributes and Category attributes: filter by an attribute’s value, using the operators below.
  • Product properties: built-in fields such as the created date, an identifier (SKU or GTIN), whether the product Has images, its Completeness, and which integration or CSV import populated its values. Completeness matches products where Some tracked attributes have no value or where All tracked attributes have a value, counted over the attributes you track for Completeness, so you can build a batch of the products that still have gaps.
For an attribute condition, pick an operator:
Is enriched, Is not enriched, and Is manually edited filter by where a value came from, not only whether one exists. This matters when a connected integration or CSV import already fills a field you also enrich, such as Description or Product type: Has data matches every product because the field is populated either way, while Is not enriched isolates the products that still need AI enrichment, and Is manually edited finds values a person set by hand.
Updated before / Updated after matches any change to the attribute’s value, not only ones from AI enrichment. An update pulled in from a connected integration (for example, a product edited in Shopify and synced to Cernel) counts too.
Has no data and Does not contain are the two you’ll reach for most when building enrichment batches. Has no data isolates the products that still need a value, and Does not contain lets you exclude products whose value already includes a term. When the field is already populated by an integration or import, reach for Is not enriched instead of Has no data to find the products AI hasn’t touched yet.
Add as many conditions as you need and join them with and or or. Switch between Simple and Advanced to keep a flat list of conditions or to group them into logic. Use Clear all filters to reset the table. When you have a setup you return to often, save it as a view from the Views button, covered in Saving and sharing a view.

Quick filter from a column header

When you only want to narrow one attribute, you don’t have to open the filter builder. Open a column’s menu from its header in the product table and use the Quick filter section to set a condition on just that attribute. It offers the same operators and value editors as the toolbar filter, so you can type a term to search within the column, or pick an operator such as Has no data or Is not enriched. Press Enter or click Apply to filter, and Clear in the same menu to remove it. A quick filter and the toolbar filter share one filter state, so anything you set here also appears as a row in the filter builder, and the table URL updates so the narrowed view survives a refresh or a shared link. A filtered column shows a funnel beside its name, giving you an at-a-glance read of which columns are narrowing the list.
A column’s quick filter reads and writes that attribute’s first condition in the filter list. If you have also filtered the same attribute inside an Advanced group, the quick filter narrows the list alongside that group’s condition, and clearing the quick filter leaves the group’s condition in place. A condition that lives only inside an Advanced group shows no funnel on its column.
To jump to an attribute’s column in a wide table, use your browser’s find (Ctrl+F, or Cmd+F on a Mac) and type the attribute’s name. Every column header can be found this way, including columns scrolled out of view, and the table scrolls sideways to the match.

Saving and sharing a view

A view saves the whole product-list setup, its filters, search, sort, and column layout, along with the taxonomy and category you have open in the sidebar, so you can return to it in one click instead of rebuilding it each time. Views live in your Cernel account rather than in the browser, so a view you save is there when you sign in from another browser or another device, and you can share one with your whole team.
1

Set up the list

Open the taxonomy and category you want the view to show, then apply the filters, search, sort, and columns you want it to remember. A view needs at least one filter, search, sort, or column choice: a category on its own isn’t enough to save.
2

Open Views and save

Click Views in the toolbar above the table, then Save view, and give the view a name.
3

Choose who can see it

Pick Only me to keep the view in your own list, or Everyone at [your organization] to share it with the whole team. Anyone on the team can apply a shared view, and anyone there can edit it.
The Save view panel open under the Views button, with a name field reading Espresso machines to review and two options: Only me (shows in your list only) and Everyone at the organization (shared with everyone, and anyone there can edit it)

Saving a product-list view and choosing whether it stays personal or is shared with the organization

Saved views appear under the Views button, grouped into My views and Views for organization. Click a view to apply it, and click it again to turn it off and return the table to its default state. A view only counts as applied once you pick it from Views: setting up the same filters by hand doesn’t light it up. As soon as the page differs from the applied view (its filters, search, sort, or column order), a Save view changes button appears to the right of Filter. Click it to write everything you changed back into the view, or click the x beside it (Discard changes to the view) to put the page back the way the view was saved. To keep the new setup as a separate view instead, use Save view in the Views menu. The Review surface has its own saved views, which you save from its Views menu.
The Catalog toolbar with the saved view Coffee products applied, the search box changed to espresso, and a Save view changes button with an x to its right, beside the Filter button

A saved view with a changed search: Save view changes writes the change into the view, and the x discards it

Column order and saved views

Drag a column header sideways to move that attribute’s column. What happens to the new order depends on whether a view is applied:
  • No view applied: the new order is saved as your own default straight away, with no button to click. Your column order and widths are stored in your Cernel account, so they’re the same when you sign in from another browser or device. They’re private to you and don’t change anyone else’s table.
  • A view applied: the drag belongs to that view and never changes your default. Click Save view changes to store the order in the view, so everyone who applies it sees the same columns. Turn the view off and your own default order comes back.
A view only carries a column order once someone has arranged one for it, so a view saved without dragging any columns shows each person their own order. Column widths are never part of a view. An order you’ve dragged on a view but not saved yet is kept if you reload the tab, so you can still save it. Press Esc during a drag, or drop outside the column headers, to put the columns back where they were. Applying a view also takes you back to the taxonomy and category it was saved on, so a view saved on one category of a custom taxonomy opens that same category even if you apply it from somewhere else in the catalog. If you switch to another category while a view is applied, the view no longer counts as applied as-is, and Save view changes moves it to the category you’re on now. Views saved before views kept the category don’t carry one, so they apply to whichever category you have open.

Enriching a large catalog in batches

A single run now covers up to 50,000 products, so most catalogs enrich in one go. When you have more than 50,000 products to enrich, work through them in batches and let each batch finish before starting the next:
1

Turn on Only enrich missing fields

In the enrichment modal, enable Only enrich missing fields. Each run then targets only products that still lack a value for the selected attributes, so finished products drop out of the next batch automatically.
2

Filter down to a batch

Use the product filters to narrow the selection to 50,000 products or fewer. For example, add a Has no data condition on the target attribute to show only products that still need a value.
3

Run and wait for it to finish

Start the enrichment and wait for the job to complete on the Jobs page before starting the next batch. Running back-to-back filtered batches in parallel can overlap on the same products.
4

Repeat until the column is empty

Re-apply the Has no data filter for products that still lack a value and run again. Repeat until no products remain. Track progress on the Jobs page and by filtering the attribute for products with no data.

Editing values in bulk

Sometimes you need to change many values by hand rather than enrich them: fixing the same wrong value across a batch of products, clearing a field before a re-run, or setting a shared value that no agent produces. Bulk select turns the product table into a grid you can select across, so you can set, clear, delete, or enrich a whole block of values at once.

Selecting the values to change

Click Bulk select in the toolbar above the table to turn on selection mode. You can then pick values in a few ways:
  • A single value: click its cell.
  • A whole product: tick the product’s row to take all of its values.
  • A block: drag across cells, or click one cell and hold Shift while clicking another to extend the range. Hold the add/remove key (Cmd on Mac, Ctrl on Windows) to add or remove cells without clearing the rest.
A bar at the bottom of the table keeps a running count of what you’ve picked, for example 3 values, 1 attribute, 3 products, and lists the keyboard shortcut for each action. Press V to turn selection mode on and off, and Esc when you’re done.
The product table in Bulk select mode with three Web Research cells highlighted across three rows, and a selection bar reading '3 values · 1 attribute · 3 products' with a red Delete button, a Bulk edit values button, and a legend of keyboard shortcuts

Setting or clearing values by hand

With a selection in place, click Bulk edit values to open the editor. The attributes you selected are listed on the left; pick one to edit. For that attribute, and for each enabled language, choose what to do:
  • Set value: type the value that every selected product should get. The field opens on the value the selection already shares, so you can see what you’re about to replace before you change it. When the selected products hold different values, or the selection reaches past the rows currently loaded, the field stays blank and tells you why, rather than showing one product’s value as if the whole selection held it. The starting value is shown, not staged: Apply still counts only the fields you actually change.
  • Clear: remove the existing value from the selected products. An attribute that must always have a value can’t be cleared.
  • Leave as is: skip the field, so nothing is written for it.
Click Apply to [n] values to write your changes. Because this overwrites the selected products and can’t be undone from the dialog, Cernel first asks you to confirm, showing exactly how many values and products it will change. Turn on Send for review to propose the edits on the Review surface instead, so they wait for approval before they’re saved.
The Bulk edit attribute values modal: the selected attribute and product count on the left, a language selector, and Leave as is, Set value, and Clear options with a text field and an Apply button
A single bulk edit covers up to a set number of values. If your selection is larger, Cernel updates the first batch and tells you how many values were left unchanged, so you can narrow the selection, or run the edit again, to finish the rest.
Variant-defining attributes (such as the size or colour that distinguishes a variant) are owned by the parent product and locked on its variants, so they aren’t yours to set on a variant here. Edit those on the parent instead. See Why can’t I edit a value? It says the attribute defines the variant.

Deleting values

To empty the selected values without opening the editor, click Delete on the selection bar, or press Del (Backspace also works). This clears the value on every selected product, across every enabled language, the same as choosing Clear for each language in the bulk editor. Because it can’t be undone, Cernel asks you to confirm, showing how many values it will delete. A value deleted by hand shows as a genuinely blank cell, not the muted No value marker that an agent leaves when it looked and found nothing.

Enriching a selection

To generate the selected values with AI instead of typing them, press E, or click Enrich Products in the toolbar while a selection is active. This uses the same agents as a full enrichment run. Enrich needs a rectangular selection, meaning the same products picked in every selected attribute, so if your selection is ragged, drag a block rather than picking single cells. Bulk select is also available on the Review surface, where you can edit or decide many proposed values together before they’re saved. See Deciding in bulk.

Moving products to a different category in bulk

A product’s category is stored as its Classification value, the same value the AI sets when it sorts products into your taxonomy. You can change it for many products at once from the product table, instead of writing a per-product prompt or re-running classification.
1

Show the Classification column

Open Column settings in the toolbar above the table and turn on Taxonomy Classification. This column is hidden by default, because the category tree in the sidebar already shows where products sit, so you switch it on only when you want to edit categories directly in the table.The Agents tab lists the attribute types, so you can show or hide whole groups of columns at once, plus Taxonomy Classification at the bottom. A Show attributes without agents option sits below the list: turn it off to hide columns for attributes that have no agent linked, so the table shows only the attributes Cernel enriches. The Tags and Product Identifiers tabs control the rest of the columns.
The product table's Column settings popover open on the Agents tab, with a checkbox per attribute type, Taxonomy Classification unchecked, and a Show attributes without agents option below the list
2

Select the products to move

Turn on Bulk select, then pick the Classification cells you want to change. Tick a product’s row to take its Classification along with its other values, or select the Classification cells across a block of rows.
3

Pick the new category

Click Bulk edit values, choose the Classification attribute, and pick the target category from the taxonomy tree. The picker has a Search field, so you can type part of a category name to find it in a deep tree instead of expanding each level. Every selected product moves to that category when you apply the change. To take the selected products out of the taxonomy instead, pick Unclassified products below the tree.
A product’s Google Product Category follows its Cernel Taxonomy category. When you move products to a different Cernel Taxonomy category, whether by bulk edit, by editing a single product, or from the Review surface, Cernel updates their Google Product Category to the matching Google category. If the new category has no Google counterpart, the product keeps its current Google Product Category.
The same confirmation and limits as any other bulk edit apply: Cernel shows how many products it will move before writing, and you can turn on Send for review to have the change wait as a proposed value on the Review surface instead of applying it straight away.

The Jobs page

Open the Jobs page from the sidebar to see a table of your jobs, newest first. Each row in the table shows:
  • Name: the job’s title (the one you set, or the one Cernel generated from the attributes and category), or its ID if untitled
  • Status: a colored badge: Pending, Running, Success, Failed, or Cancelled
  • Progress: how many elements are done out of the total (for example, 42 / 100)
  • Trigger: how it was started, by an Automation or run manually
  • Created by: the teammate who started the job
  • Created: when the job started
  • Actions: rename the job at any time, and cancel the job while it’s still running
Click any row to open that job’s proposed values on the Review surface, already scoped to the job. The Jobs page itself is for tracking. All approve, edit, and reject actions happen on Review.
The Jobs page showing the search box and the Status, Trigger, Created by, Product, and date filters above a table of jobs with Name, Status, Progress, Trigger, Created by, and Created columns, and a rename (pencil) action on every row
A job-status indicator sits in the app header and stays visible while you’re signed in, so you can keep an eye on active work from anywhere in the app. It spins while jobs are running and shows a count of active jobs. Click it to open the Running jobs list, jump straight to a job, or choose View all jobs to go to the Jobs page.

Finding a job

A search box and a row of filters sit above the table so you can narrow a long history to the run you’re after:
  • Search jobs by name to match on the job title
  • Status: show only Pending, Running, Success, Failed, or Cancelled jobs
  • Trigger: show only jobs started by an Automation or run manually
  • Created by: show only jobs a particular teammate started
  • Product: show only jobs that ran on a specific product
  • From and To: limit to jobs created within a date range
Use Clear filters to reset them all at once.

Renaming a job

Every job can be renamed, whatever its status. Enrichment setup has several steps and the job title is easy to skip past, so you can give a run a clearer name after it has started, or even once it has finished. In the Actions column, click the Rename job action, type a new Job name, and click Save. The new name appears everywhere the job is shown, including the header job-status list. A blank name, or a name you haven’t changed, can’t be saved.

Cancelling a job

While a job is Pending or Running, a Cancel job action appears in its Actions column. Cancelling stops the run: anything already finished is kept, but the remaining items aren’t processed, and this can’t be undone. Cernel asks you to confirm (Cancel job to go ahead, or Keep running to leave it) before stopping the job. Finished jobs (Success, Failed, or already Cancelled) have nothing left to stop, so they show no cancel action.

Older jobs

Jobs run before the Jobs & Review update are kept available under Show older jobs at the bottom of the page. Expand it to browse your earlier history; collapse it again with Hide older jobs.

Recent jobs on the Dashboard

The Dashboard’s Recent jobs widget shows the most recent runs at a glance, with the same status and progress information. Use it to jump to the full Jobs page when you need the complete history.

Job statuses

A finished job (Success) doesn’t mean its values are live. If the run had Review turned on, the proposed values wait for your approval on the Review surface (see below).

Reviewing proposed values

When a run has Review turned on, the values your agents generate aren’t saved straight away. They wait on the Review surface as proposed values until you approve, edit, or reject them. This is where you decide what actually goes live on your products.

Where Review lives

There are two ways into Review:
  • From the Catalog: open Catalog in the sidebar, then at the top of the page switch between Catalog (browse your products) and Review (work through proposed values). The switch keeps whichever category you have selected, so you can jump straight from a category’s products to that category’s review queue. Pick categories from the taxonomy tree in the sidebar to narrow what you’re reviewing.
  • From a job: click any job on the Jobs page to open the review queue scoped to just that job’s products. A Back to jobs link returns you to the Jobs page.

The review queue

The review queue lists one row per product, with a card for each proposed value. Every card shows the attribute, the proposed value, the language, and a status badge: When an agent produced the value, the card also names that agent at the bottom, so you can tell which agent to adjust without looking the product up. Click the name to open that agent in the Agent Sandbox and adjust it. Hover the name to see it in full if it’s cut short. Values with no recorded agent, such as older values or values that came from an import, show no agent name. Use the toolbar to focus the queue:
  • Search by product name
  • Languages: show only the languages you want to review
  • Filter by job: narrow to a single job’s products
  • Attribute filter: hide or show value cards by attribute
  • Status: show only values with the statuses you pick, for example only Failed values, or In review values alone. You can pick In review, Approved, Failed, and Skipped (plus Rejected when review steps are on). Approved shows values a reviewer approved together with values an enrichment job saved straight away without needing review, so you can look back at what’s already gone through and step through those products in the detail view. Values from imports and manual edits in the Catalog don’t count as Approved. While you review a single job, Rejected is offered too. Leave it empty to see every value that still needs work (everything except Approved); in a single job’s review, an empty filter shows every value of the job. Your choice is remembered between visits, saved with a saved view, and reset by Clear filters
  • View options: let each card grow on a sideways-scrolling row, or lay values out in a column per language
Review has no product filter builder of its own. Filters you carry over from the Catalog (through the Catalog / Review switcher) or from a saved view still narrow the queue, and Clear filters removes them. To change them, adjust the filters on the Catalog and switch back to Review.
The Review surface: the Catalog / Review switcher at the top, the product and review filters (languages, jobs, attributes, and status), and the queue listing products with their proposed-value cards and bulk Dismiss, Reject, and Approve actions

Approving, rejecting, and dismissing

You have three actions, depending on a value’s state:
  • Approve: accept the proposed value; it replaces the product’s current value for that attribute.
  • Reject: discard the proposed value; the product’s current value is left unchanged.
  • Dismiss: acknowledge a Failed or Skipped value. There’s nothing to approve or reject, so dismissing simply clears it from your queue once you’ve seen it.
Both Approve and Reject let you add an optional comment to record why you made the call, useful for teammates reviewing the same catalog later. To work quickly, select multiple cards (or whole product rows) and use the bulk Approve, Reject, or Dismiss buttons. To decide the whole queue in one go, use the header select all: this reaches every in-review value that matches your current filters, including products beyond the ones loaded on screen, so you don’t have to scroll to the bottom first. When you’re reviewing a single job, select all covers that job’s entire pending set the same way. You can still deselect individual products to leave them out. Select all followed by Dismiss only dismisses values with the statuses currently shown, so with Failed picked, skipped values are left alone. When a bulk decision spans many products at once, Cernel asks you to confirm before applying it.
To clear out the values that didn’t generate after a new job, pick Failed and Skipped under Status, select all, and Dismiss them. Then pick In review to work through only the decisions you still owe.

Reviewing one product in detail

Click a product (or open a single value) to go to its detail view, which lays everything out in three columns:
  • Current value: what’s saved on the product right now. Approving a proposed value replaces it.
  • Pending · In review: the proposed values awaiting your decision. Select one to inspect it.
  • Inspector: everything behind the selected value, so you can decide with full context.
The product review detail view with three columns (Current value, the Pending in-review proposed values, and an Inspector showing the value's status, language, translation source, and the Used attributes, Reasoning, and Prompt tabs), with Previous, Next, and Approve all controls in the header
The Inspector shows the value’s status, attribute, language, source (for example, AI enrichment), and date, with Generated by naming the agent that produced it when one is recorded. Click the agent name to open that agent. If the value was translated, it notes which language it was translated from. Three tabs explain how the value was produced:
  • Used attributes: the product data the agent fed into its prompt as inputs
  • Reasoning: the agent’s own explanation of why it generated this value
  • Prompt: the exact compiled prompt, including any images, that produced the value
From here you can Approve or Reject the selected value (with an optional comment), edit it inline before approving, or use Approve all to accept every still-pending value on the product. Previous and Next move you through the products in your current queue or job without returning to the list. The detail view follows your Status filter: it shows only values with the statuses you picked, and Previous and Next step through the same filtered list. When you edit a value inline, the editor matches the attribute’s type. An HTML value opens in the rich-text editor, so you format the description directly (bold, lists, links) instead of typing markup, with a toggle to switch to the raw HTML source whenever you need it. If a value contains HTML the rich-text editor can’t keep exactly as it is, such as inline styles, images, or tags written by another system, it opens as HTML code with a yellow notice instead, so saving never rewrites markup you didn’t touch. A taxonomy classification value shows an Edit button that opens the category picker, so you can move the product to the right category straight from Review without typing anything, or pick Unclassified products to leave it without a category. The picker has a Search field for finding a category in a deep tree without expanding each level. The classification picker is available for your Cernel Taxonomy and any custom taxonomies. An external standard such as Google Product Category carries no editable category tree, so it has no Edit button. Both the value editor and the category picker offer Save and approve next to Save. Use it when your edit is the final answer: it saves the value and approves it in one step, so it doesn’t sit in the queue waiting for a second click.
When you’re reviewing a single job, decided values stay visible in place, marked with their decision, instead of disappearing. In the general queue, a product drops out once you’ve resolved its values.

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:

Advanced configuration

Click a job on the Jobs page to open the review queue scoped to just that job’s products. In this job-focused view, values you’ve already decided stay visible in place, marked Approved or Rejected, so you can see the full picture of what the job produced. A Back to jobs link takes you back to the Jobs page when you’re done.
If your organization has multiple languages enabled, agents generate values for each configured language, and each value shows its language. Use the Languages filter in the review toolbar to focus on one or more languages, or switch on Language columns in View options to lay each product’s proposed values out in a column per language. Manage languages in Tools > Languages & markets.
Select multiple value cards, or tick a whole product row to select all of its values, then use the bulk Approve, Reject, or Dismiss buttons. You can attach an optional comment to a bulk Approve or Reject. When a decision spans a large number of products at once, Cernel asks you to confirm before applying it.Use the header select all to decide the entire queue at once. Cernel resolves this against your current filters (languages, attributes, and, in a job review, the job in focus), so it approves or rejects every matching in-review value, including products beyond the ones currently loaded on screen. Deselect individual products first if you want to leave them out, and the confirmation dialog will note how many you excluded.
Not every value generates successfully. Failed values are ones the agent couldn’t produce; Skipped values are ones it had nothing to generate for. These can’t be approved or rejected; instead, Dismiss them to acknowledge you’ve seen them and clear them from your queue. Pick Failed or Skipped under Status to see only those; pick In review to see only values awaiting a decision.

Frequently asked questions

Open the job from the Jobs page to see its status, and check the review queue for any values marked Failed. Common causes:
  1. Agent configuration issue: the linked agent’s prompt may be empty or invalid
  2. Missing dependencies: a required attribute dependency isn’t enriched yet
  3. API error: a temporary issue with the AI provider
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.
Cernel stops and asks first, so an unsaved edit is never lost silently. If you change a value inline and then approve (on its own or with Approve all) without saving, a You have unsaved changes dialog appears, and the edited card is marked Not saved yet so you can spot it. You then choose:
  • Save and approve: keeps your edit, saves it, and approves that value.
  • Approve without saving: approves the value as the agent enriched it and discards your edit.
Nothing is approved until you pick one, so you can also cancel and go back to your edits.
Enrichment no longer fails just because a single image is unusable. If an image can’t be fetched, isn’t a valid image, or is unusually large, Cernel skips that one image and generates the value from the product’s remaining inputs (its other images, text, and attributes). A run only fails when nothing usable is left to work from.When an image is skipped, the agent records a short note in its Reasoning, for example “A product image was not processed (the image exceeds the size limit)” followed by the image’s address. Open the value in the review detail view and check the Reasoning tab to see it. If a generated value seems to be missing detail you expected from a photo, this note is the first place to look.The agent is also told, before it answers, which images didn’t load and why (for example, the image server refused the request, or the link wasn’t found). It’s instructed not to describe or guess at a photo it never saw. If a value needed that image, for example a color that only shows in the photo, the reasoning says the image couldn’t be loaded instead of inventing what it shows. Fix the image link or make the image publicly reachable, then enrich the product again.This applies to agents that write text values and classifications. A Media agent that generates a new image still needs its source image to load: if it can’t, that value fails.
Yes, while it’s still Pending or Running. Open the Jobs page and use the Cancel job action in that job’s Actions column, then confirm. Cancelling stops the run: anything already finished is kept, but the remaining items aren’t processed, and it can’t be undone. Once a job reaches Success, Failed, or Cancelled, there’s nothing left to stop, so no cancel action is shown. See Cancelling a job.
Yes. The Configure Enrichment modal has an optional Title field. Whatever you type there becomes the job’s Name on the Jobs page, so a run is easy to find later. Leave it blank and Cernel names the job for you from the attributes and category you selected (for example, Color from Electronics). You can also rename a job later, in any status: use the Rename job action in its Actions column on the Jobs page. See Renaming a job.
Reject is a decision about a value the agent did generate: you’re declining to save it, and the product keeps its current value. Dismiss applies to Failed or Skipped values, where there’s nothing to save in the first place; dismissing just acknowledges you’ve seen them and removes them from your queue.
They wait on the Review surface as proposed values until you act on them. Nothing is saved to your products or synced to your integrations until you approve it. Reach Review from the Review tab at the top of the Catalog, or by opening a job from the Jobs page. The starting position of the Review toggle in the enrichment modal follows your organization’s approve-before-push setting (in Settings > Platform), and you can override it for any individual run.
Changing the organization’s approve-before-push setting only affects future runs: it sets the default position of the Review toggle when you start an enrichment. It does not retroactively approve or push values that are already waiting in Review. Those still need a decision: approve them from the Review surface, or reject them if you don’t want them.
Each enrichment run processes up to 50,000 products in a single job, so most catalogs enrich in one go. If you select more, only the first 50,000 are enriched in that run and the rest are silently skipped. For catalogs larger than that, enrich in runs of 50,000 or fewer, turning on Only enrich missing fields and waiting for each job to finish before starting the next. See Enriching a large catalog in batches.
The product table tells two kinds of blank apart, so you can see whether an agent has looked at an attribute yet:
  • An empty cell means nothing has ever been written for that attribute on that product. Enrichment hasn’t produced a value here.
  • A muted “No value” means an agent did run and deliberately produced nothing, because it found nothing to write for that attribute. It carries the same enrichment tint as any other AI-written value, so you can tell it apart from an untouched cell.
Hover over the value to open its details popover and confirm the source. If you expected a value where you see No value, check the agent’s prompt and the product’s inputs: the agent ran but had nothing to go on.
Yes. Click Bulk select in the product table toolbar, pick the cells, rows, or columns you want (drag or Shift-click to take a block), then click Bulk edit values to Set value, Clear, or Leave as is for each attribute and language. This writes the values directly, so use Send for review in the editor if you’d rather have them approved first. To empty the selected values outright, click Delete (or press Del) instead of opening the editor. See Editing values in bulk.
No. Writing values in the bulk editor overwrites the selected products and can’t be undone from the dialog, which is why Cernel asks you to confirm the count first. If you want a safety step, turn on Send for review so the edits wait as proposed values on the Review surface until you approve them.
Yes. Saved views are stored in your Cernel account, not in the browser, so a view you save is there when you sign in from another browser or another device. The same goes for your own column order and widths in the product table. When you save a view you choose who can see it: Only me keeps it in your own list, while Everyone at [your organization] shares it with the whole team, and anyone there can apply or edit it. You save and manage views from the Views button on the product list; see Saving and sharing a view. (This replaces the earlier saved filters, which were kept only in the browser you saved them in.)
A saved view was applied. While a view is applied, every column you drag belongs to that view, and your own default order stays as it was. Click Save view changes to keep the order in the view, or click the x to discard it. To change your default order, turn the view off first (click it again under Views), then drag the columns. See Column order and saved views.
Yes. When you save a view, Cernel stores the taxonomy and category selected in the sidebar together with the filters, search, sort, and columns. Applying the view switches the sidebar back to that taxonomy and opens that category, wherever you are in the catalog when you apply it. Views saved before this was added don’t carry a category, so they apply to the category you currently have open. See Saving and sharing a view.
The product table’s search matches either the title or an identifier (SKU or EAN), not a mix of the two in one search. Skinny Jeans VI071BL finds nothing, while Skinny Jeans or VI071BL on its own finds the product. Title words can be typed in any order. See Searching the product table.
Yes. Paste the SKUs (or EANs, or any other identifier) into the product table’s search box, separated by commas or one per line, and the table shows every product whose identifier is exactly one of them, up to 5,000 values per search. Because a comma turns a search into a list, a title search that contains a comma finds nothing: search Jeans blue rather than Jeans, blue. See Searching for a list of identifiers.
Yes. The Google Product Category follows the product’s Cernel Taxonomy category, so when you change the category yourself (inline, with bulk edit, or while reviewing a proposed value), Cernel updates the Google Product Category to match, the same way it does after AI classification. If the category you picked has no Google counterpart, the existing Google Product Category is left as it is. See Moving products to a different category in bulk.
Yes. By default the product table’s search and filters match parent products only. Turn on the Search within variants toggle in the product table toolbar to widen the match to product variants as well, so you can land on an individual variant. The toggle stays disabled until you enter a search term or apply a filter, since it needs something to match against.With it on, each matching variant appears under its parent product, with extra columns for the properties that set that variant apart and the matched text highlighted, so you can see exactly which children matched and why.Filters test each variant against the values it inherits from its parent. A variant with no value of its own for an attribute is treated as having its parent’s value, so a filter such as Brand is Osprey also matches the variants of an Osprey product. Negative filters follow the same rule: Is missing does not match a variant that inherits a value. Inherited values appear dimmed in the table, and hovering one shows Inherited from the parent product. A variant’s own value, even an empty one, always takes priority over its parent’s. Where an attribute’s Variants inherit this from their parent setting is off, variants are matched on their own values only (see Enrich variants from their own data only).When you enrich, bulk edit, or export every match while Search within variants is on, the same matching carries over and the Product Scope is measured from each match: Selected products only runs on exactly the products and variants the table shows (this is the default in this case), Include product variants adds everything below each match, and Product variants only runs only on what sits below the matches. See Running enrichment for the scope options. Automations offer the same toggle, see Variants and inherited values.
Yes. When you edit a proposed HTML value on the review detail view, it opens in the rich-text editor, so you format the text directly with bold, lists, and links instead of writing markup. A toggle switches to the raw HTML source if you would rather edit that. Click Save and approve to save your change and approve it in one step, or Save to approve it later.
The rich-text editor only opens a value it can save back exactly as it is. Some HTML would change if the editor rebuilt it, for example inline styles, images, <b> and <i> tags, wrapper <div> or <span> elements, or tables written outside Cernel. Those values open as HTML code with a yellow notice, and the rich/plain toggle is hidden, so you edit the markup directly and nothing else in the value changes. Most values generated by your agents, including bulleted lists, still open in the rich-text editor. This applies everywhere you edit an HTML value: in Review, on the product page, and in the product table.
Yes. On the review detail view, a proposed taxonomy classification value has an Edit button that opens the category picker, so you can move the product to the correct category straight from Review and then approve it, without leaving for the product table. The picker works for your Cernel Taxonomy and any custom taxonomies. A classification against an external standard such as Google Product Category has no category tree to navigate, so it has no Edit button.
Yes. When you enrich variants (with a Product Scope of Include product variants or Product variants only), their proposed values wait for a decision on the Review surface just like a parent product’s. Selecting a category in the sidebar, or applying a search or filter, keeps the variants in view: each variant lists as its own row alongside its parent, and you approve, edit, or reject its values the same way.Bulk actions cover variants too. When you use the header select all to decide a whole category or a whole job, every matching variant value is included, not only the parent products. For variant-heavy catalogs this means the queue can show many more rows than you have parent products, since each enriched variant contributes its own.
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 Tools > Languages & markets.
Turn on Only enrich missing fields in the enrichment modal. When this toggle is on, the AI only generates values for attributes that have no value yet; existing values you’ve reviewed or hand-edited are left alone. Turn it off to re-enrich every selected attribute, overwriting current values.
Cernel decides a field is missing by whether a value has ever been saved for it, not by what that value looks like. A field with any saved value counts as filled and is skipped, even when that value is blank, for example one you cleared by hand or a blank that came in from an import. A field like that can look empty in the table and still be left untouched by the run.The check runs per language, so on a multi-language attribute one language can be filled and skipped while another is still missing and gets enriched in the same run.On a variant, a value it inherits from its parent counts as filled, so the field is skipped. The exception is an attribute whose Variants inherit this from their parent setting is off: there, only the variant’s own value counts.To re-generate a field that already holds a saved but empty value, turn Only enrich missing fields off for that run. You can narrow the run to those fields first by adding an Is empty filter (see Filtering the product list).
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.
Jobs remain visible on the Jobs page. Recent runs appear at the top; earlier history, including jobs from before the Jobs & Review update, is available under Show older jobs. The Dashboard’s Recent jobs widget gives you a quick view of the latest runs with a link through to the full page.

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 start jobs by hand.