Skip to content
Learn › Clean and shape data: open the docs menu

Use AI to classify, enrich or translate a column

Generative AI writes values into a column from a plain-English prompt, so you can classify, enrich, summarise, translate or reformat rows without leaving the Data Editor. Open a View, click the blue + button and choose Generative AI in the AI Powered category. The result is saved as a pipeline task, so it runs again whenever your data refreshes.

Before you start

You don't need your own AI key. If your workspace has no external keys, Generative AI uses a key that Mammoth provides, and the panel shows no key selector. To choose the provider and model yourself, a Workspace Owner adds a key for OpenAI (ChatGPT), Anthropic (Claude), Google (Gemini) or xAI (Grok) in Workspace Settings > API Keys (Add your own AI provider key). The panel then shows an API key selector.

Open Generative AI

  1. Open a View in the Data Editor.
  2. Click the blue + button (tooltip "Add a task") in the action bar, or a + button in the Pipeline panel. The Transform menu opens on the AI Powered category.
  3. Click Generative AI. The panel opens at the bottom of the View.
Transform menu open on AI Powered, listing Ask in plain words, Generative AI, Extract Text, Bulk Replace and Conditional Filter Generative AI panel with an empty prompt box, a column selector, an API key picker showing a Gemini key, and a Preview button
ElementWhat it does
Prompt boxDescribe the values you want in plain English
Limit note"Max 300 chars per cell, applies only to the first 50,000 rows."
Column selectorChooses which columns the AI sees as context (automatic or manual)
API key selectorPicks a saved external key and its provider. Shown only when the workspace has external keys.
PreviewGenerates a sample without changing the dataset. Active once there is a prompt (and a key, if the workspace has keys).
Apply results intoSets the destination column and whether it is new or existing
ApplyRuns on the full dataset and adds the pipeline task

Fill a column with AI from a prompt

  1. Type your instruction in the prompt box: what you want and what the output should look like.
  2. Choose the context columns, or leave automatic selection on.
  3. If the workspace has keys, pick one in the API key selector. Keys are grouped by provider, with the provider's logo and name and the key's display name. A key problem, such as a rate limit, shows as a banner at the top of the panel.
  4. Click Preview and check the 10 sample rows.
  5. Under Apply results into, choose New Column and type a name, or choose Existing Column and pick one to overwrite.
  6. Click Apply.
API key dropdown open in the Generative AI panel, listing an Anthropic key

On Apply, Mammoth sends the prompt and context columns for each row to the AI provider (with the selected external key, or a key Mammoth provides) and writes the returned values into the output column. The column appears in the grid and a Generative AI task card in the Pipeline panel. How long it takes depends on the number of rows, the provider and the model. The task re-runs on future refreshes and whenever the pipeline runs again.

Pipeline panel with a Generative AI task showing its prompt and new column, and the data grid updated

Example prompts for Generative AI

GoalExample prompt
ClassifyBased on the Ship to Country, classify the shipping destination as Europe, UK, or Other
CategoriseCategorize the product description into one of: Electronics, Apparel, Home, Food
EnrichGenerate a short 1-sentence description of this product based on its name and category
TranslateTranslate the customer comment from Spanish to English
NormaliseStandardize the company name: remove Inc, Ltd, LLC suffixes and trim whitespace
ScoreRate the sentiment of this review as Positive, Neutral, or Negative

Each value must be 300 characters or fewer. If the model returns longer values, the run fails with an error.

Choose which columns the AI reads

  • Auto select columns for evaluation: Mammoth picks the columns most relevant to your prompt. If your prompt mentions "Ship to Country", that column is selected.
  • Manually select columns for evaluation: pick them yourself, when automatic selection picks columns that could confuse the model, you want more consistent results, or column names are similar.

More columns take longer to process. You can select up to 20. With more, the panel shows "25 columns selected. Max 20 allowed" until you remove some.

Preview AI results before you apply

Preview generates 10 sample rows in a Generated column, without changing your dataset or adding a task. Generative AI doesn't use the live preview most functions show above the panel: its Preview runs only when you click it, because each preview calls the AI provider.

Generative AI panel with a prompt to classify shipping destination and a preview column of Europe and UK values

Generative AI limits

LimitValue
Output per cell300 characters
Rows processedThe first 50,000 rows of the View. Rows after that are not processed.
Context columns20

See Limits and quotas for all Generative AI limits.

Troubleshooting Generative AI

SymptomCauseFix
The run fails with an error about lengthA returned value is over 300 charactersAsk for shorter output in the prompt
Only part of the View has valuesOnly the first 50,000 rows are processedFilter the View to 50,000 rows or fewer before this step
Apply stays offNo column name, no prompt, or no key selected in a workspace with keysFill in the missing item
Results don't match what you meantThe prompt is unclearMake it more specific, check a few rows, and compare with a manual step

Key messages (rate limits, invalid keys, no quota): see Add your own AI provider key.

Was this page helpful?

Something wrong? support@mammoth.io