Spot missing required information
Check missing required fields, incomplete products and category completeness. Use your category and attribute setup to understand which product records need attention.
← All featuresCatalogue quality and insights
Find the gaps. Improve the information that matters.
See missing required information and category completeness, validate incoming product data and understand how your team uses AI. Start with visible catalogue gaps and choose the next improvements with confidence.
The catalogue problem
A complete field is a starting point. Useful information is the goal.
Missing attributes can weaken filters and comparisons. Unclear content leaves purchase questions unanswered. Quality work is easier to act on when your team can see what is missing, validate incoming changes and review the usefulness of AI suggestions.
Review imports before applying them
Inspect validation results before product data is written. See which records would be created, updated or skipped, then correct issues and rerun the import.
Understand AI usage and decisions
AI Insights shows usage and suggestion outcomes, including acceptance, edits and credit spend. Use these signals to judge content-workflow usefulness and refine your AI Context.
Check the result in the connected shop
Inspect product synchronisation status and results after sending approved information. Confirm that the intended product updates reached the connected shop.
How it works
From product information to an approved improvement.
A practical workflow around the catalogue you already operate, with human review before consequential AI changes are applied.
- 01
Choose a useful starting point
Inspect required-field gaps and category completeness. Select a manageable set of products or a category where the missing information affects the customer experience.
- 02
Improve and validate
Check source information, maintain attributes and use supported AI content workflows. Review proposed content and import findings before applying changes.
- 03
Review the progress
Recheck completeness, inspect synchronisation results and review AI usage. During beta, compare the catalogue improvements and work involved with our team.
Product scope
Practical quality checks today. Deeper intelligence as the next step.
Use the available workflow in the beta. The broader direction is shown separately so you can judge fit against what you need now.
What you can work with now
- Missing-required-field and category-completeness checks.
- Import validation with record-level findings, corrections and revalidation.
- AI usage and suggestion-decision metrics, plus product synchronisation results.
Where we are taking it next
- AI-generated recommendations for which catalogue improvements to prioritise and why.
- Historical catalogue-quality trends and broader checks for contradictions, stale values and cross-shop discrepancies.
- Stronger measurement connecting catalogue improvements with operational and commercial outcomes.
Questions before you connect
A clearer picture of the workflow.
Does completeness mean the information is correct?
No. A field can be filled and still contain an inaccurate or unhelpful value. Completeness helps locate gaps; source verification and human review remain necessary.
Does AI automatically prioritise the catalogue work?
Current completeness checks identify required-field gaps. A general AI workflow that recommends and explains catalogue-wide priorities is a product direction, not a current feature claim.
Can I see a conversion uplift in AI Insights?
AI Insights measures AI usage and suggestion decisions. It is not a conversion-attribution dashboard. We can review catalogue improvements during beta, but commercial impact needs separate measurement.
Works together
The rest of the catalogue workflow.
Founding Customer Beta
Start with a clearer view of your catalogue.
30 days free, hands-on onboarding and real work on your own catalogue. Tell us about your shop, test meaningful improvements and share feedback with our team.
Request beta access