In e-commerce and marketplace workflows, files often arrive with hundreds or thousands of rows — and many required fields are empty. Filling them manually is tedious and error-prone.
Fill the Gaps solves this: WeTransform's AI scans the data already present in your file and automatically fills in the missing values, column by column.
🛒 A concrete example
Imagine you receive a product catalog with 2,000 items. Your target format requires 15 attributes per product — but your supplier only fills in 6. The rest are empty.
If your file has a rich product description column, Fill the Gaps can read it and extract the missing values: product type, material, dimensions, weight, target audience — all inferred from the description and populated automatically.
🤖 Fill the Gaps works from context. The AI looks at the information you point out, present in each row, such as: description, title, other attributes — and uses it to fill in what's missing. The richer your source data, the more accurate the results.
⚙️ How to use Fill the Gaps
Fill the Gaps is available as a rule action in the Rules editor. Open the Rules editor, create a new rule, and in the THEN section select "Fill the gaps using AI".
Configure which target column you want to fill, and which source columns the AI should use as context. You can apply Fill the Gaps to multiple columns in the same rule — one action per column to fill.
✅ Reviewing the results
Once the rule runs, the filled values appear in Finalize. You can review them row by row, correct any that don't look right, and submit when you're satisfied.
💡 Fill the Gaps uses AI credits. Each row filled consumes credits from your account balance. You can monitor your remaining credits in your account settings. Results are always reviewable before submission — you're never locked into what the AI generated.
🏭 Other use cases
📦 Product catalogs — fill missing EAN codes, dimensions, or weights from product descriptions
📋 Appointment data — infer appointment type or location from notes fields
🧾 Invoice processing — extract payment terms or due dates from unstructured text
👤 Contact data — derive job title or company size from available context
👉 What to do next