Tomat Documentation
Tomat HomeCommunity
  • đź‘‹Introduction to Tomat
  • Getting Started
    • Product Updates
    • Beginner's Guide
    • FAQ
  • Product overview
    • Home Page
    • Exploring Data
      • Data Catalog
      • Exploring Datasets
      • Statistics Panel
    • Designing Flows
      • Creating Flows
      • Flow Designer Guide
        • Working with Canvas
        • Using Groups
        • Working with Table
      • Managing Flows
      • Demo: Building a Simple Flow
    • Executing Flows
      • Running Flows
      • Jobs overview
    • Building Reports
      • Designing Reports
      • Running Reports
      • Reports Page
    • Tomat Use Cases
  • Data Transformation
    • Transforms
      • Source
      • New Empty Table
      • Output
      • Chart
      • New Column
      • If...Then
      • Rolling Functions
      • Column Type
      • Columns Edit
      • Sort
      • Filter
      • Remove Duplicates
      • Split Text
      • Extract Text
      • Find and Replace Text
      • Match Text
      • Join
      • Union
      • Group By
      • Pivot
      • Unpivot
      • To JSON
      • From JSON
      • API Call
      • Use AI
    • Formulas
      • What are Formulas?
      • Math Functions
        • Abs
        • Ceiling
        • Exp
        • Floor
        • IsEven
        • IsOdd
        • Ln
        • Log
        • Log10
        • Mod
        • Pi
        • Power
        • Quotient
        • Round
        • RoundDown
        • RoundUp
        • Sign
        • Sqrt
        • Truncate
      • Trigonometric Functions
        • Acos
        • Asin
        • Atan
        • Atan2
        • Cos
        • Cot
        • Degrees
        • Radians
        • Sin
        • Tan
      • String Functions
        • Compare
        • Concat
        • Contains
        • In
        • CountMatches
        • CountMatchesRegexp
        • EndsWith
        • EndsWithRegexp
        • Extract
        • FindMatchOfString
        • FindMatchOfRegexp
        • FindMatchesOfString
        • FindMatchesOfRegexp
        • Left
        • Length
        • Lower
        • Matches
        • Pad
        • ProperCase
        • RemoveSymbols
        • RemoveWhitespaces
        • Repeat
        • Replace
        • ReplaceRegexp
        • Reverse
        • Right
        • Spaces
        • Split
        • SplitRegexp
        • StartsWith
        • StartsWithRegexp
        • Stuff
        • Substring
        • SubstringDelimiter
        • SubstringRegexpDelimiter
        • Trim
        • Upper
      • Date & Time Functions
        • Date
        • DateAdd
        • DateAdd
        • DateDiff
        • DateDiff2
        • DateFromParts
        • DateTime
        • DateTimeFromParts
        • DateTrunc
        • DayName
        • DayOfMonth
        • DayOfWeek
        • DayOfYear
        • Hour
        • Minute
        • Month
        • MonthName
        • Now
        • Quarter
        • Second
        • Time
        • TimeFromParts
        • Today
        • Week
        • Year
      • Aggregate Functions
        • Array
        • ArrayIf
        • Avg
        • AvgIf
        • Count
        • CountA
        • CountIf
        • CountUnique
        • Max
        • MaxIf
        • Median
        • MedianIf
        • Min
        • MinIf
        • Mode
        • ModeIf
        • Percentile
        • Quartile
        • StdDev
        • StdDevIf
        • Sum
        • SumIf
        • SumProduct
        • Variance
        • VarianceIf
      • Conversion Functions
        • ToArray
        • ToBoolean
        • ToDate
        • ToDateTime
        • ToDecimal
        • ToInteger
        • ToObject
        • ToTime
        • ToString
      • Misc Functions
        • At
        • IsMissing
        • RowNumber
        • Random
        • If
        • Coalesce
        • True
        • False
        • Null
        • $target
      • Window Functions
      • Custom Functions
      • Data Types
      • Supported Date Parts
      • Regex: List of Tokes
  • PRICING & BILLING
    • Plans, Subscriptions, and Credits
  • Integrations
    • Connectors
      • Data Storages
        • PostgreSQL
        • Snowflake
      • Data Sources
  • Tutorials
    • Merge Columns
    • Join Types
    • Union Introduction
    • Window Functions
    • What is Unpivot?
    • JSON Format Tutorial
    • Using Regex
Powered by GitBook
On this page
  • Overview
  • How It Works
  • 1. Write a Prompt
  • 2. Choose a Model
  • 3. Web Search (Optional)
  • 4. Set Output Columns
  • 5. Execute the Prompt
  • 6. Edit or Regenerate Rows
  • Tips for Best Results
  1. Data Transformation
  2. Transforms

Use AI

Calls AI for each row to extract, enrich or cleanup.

Overview

The Use AI node helps you run an AI model on your table, row by row. You write a prompt, pick a model, and the node returns the results for every row in new columns.

How It Works

1. Write a Prompt

Describe what you want the AI to do for each row in the prompt box. Use @ColumnName to pull in values from your table.

Example:

Visit @CompanyDomain and find their ICP titles. Return them as a comma-separated string.

2. Choose a Model

Select the AI model you want to use from the drop-down menu. Not all models support web search

3. Web Search (Optional)

Turn on web search if your prompt needs fresh information from the internet. If the chosen model does not support web search, this option will be disabled.

Set the search depth to Low, Medium, or High:

  • high Most comprehensive context, highest cost, slower response.

  • medium (default) Balanced context, cost, and latency.

  • low Least context, lowest cost, fastest response, but potentially lower answer quality.

4. Set Output Columns

Add as many output columns as you need. For each column, set its name, type (String, Integer, Boolean, etc), and optional description to help AI.

You can use “Generate from prompt” to let the AI suggest columns based on your prompt.

If you don’t add any columns, the node will automatically create them based on the AI’s first response.

Switch to JSON schema view if you want to see or edit all columns as JSON.

5. Execute the Prompt

You can run the node on all rows, just one row, or selected rows. An alternative way to get the result for a specific row is to find any output column in the table preview and click the "Generate row" link.

The node works row by row, passing each row’s values to the prompt and writing back the results.

6. Edit or Regenerate Rows

After the run, you can manually edit, add, or delete values in the output columns. You can also re-run the node for any specific rows directly from the table, without affecting other rows.

Tips for Best Results

Test your prompt

Start by running the node on one or a few rows to see if you get the desired output. Adjust your prompt or output columns before running it on the whole table. We recommend always using this option first. When you are ready, press the "All rows" button to return values for all remaining rows. It will not refill rows already containing the result.

One row at a time

The node works with only one row at a time. It cannot calculate aggregations, compare, or group rows.

Changing output columns

If you want to change the output columns after a run, reset the results.

Web search and credits

Using a web search will use more credits. Only turn it on if your prompt actually needs it.

Model limits

Each model has its limit for how much text it can process. Try a shorter prompt or pick a different model if you hit an error.

Show only affected columns.

Use the "Show only affected columns" toggle below the table to show only the columns used in the prompt or set as output columns and hide all other columns.

Last updated 3 days ago