Skip to main content
Enhancement lets you use AI to fill in, improve, or transform column values after extraction. This is useful for generating descriptions, translating content, or enriching data with web-sourced information.

How enhancement works

  1. Select rows and a column — Choose which rows to enhance and which column to fill.
  2. Write a prompt — Describe what the AI should generate, using context from other columns.
  3. AI processes each row — The model reads the row’s existing data and generates a value.
  4. Results are written back — Enhanced values replace or fill the target column.

Enhancement types

Content generation

Generate new content based on existing data:

Translation

Translate content to another language, optionally using your glossary:
Set target_language and use_glossary: true to apply your glossary terms during translation.

Web research

Enable web_search: true to let the AI search the web for additional information:

Single column vs bulk

Tracking progress

Enhancement runs asynchronously. Check progress with:

Credits

Each enhancement consumes credits. Regular single-column enhancement costs 2 credits per row; regular bulk enhancement costs 0.5 credits per column. Gallery Max image columns use a separate 16-credit rate, which the current bulk estimate does not reflect. Check your balance via the Credits API.

Traces

Recorded traces can include the prompt, configured model, confidence score, tool calls, sources, response text, and a summarized thought. They do not expose private chain of thought. See Row traces for details.

Enhance descriptions with a template

For a rich-text column, select a content template, configure fixed values, linked columns, or AI instructions, and save the column changes before running enhancement. Template previews are free; generating product content uses credits. Editing the library template does not regenerate existing products. See Credits & billing for balances, packages, and expiry rules.