AI Column Types and When to Use Each

This article describes the different AI Column modes available in TexAu and when to use each one.

What an AI Column does

An AI Column sends data from your table to an AI model and writes the model's response into a new column. Use it to classify, summarize, extract, score, or transform text at scale.

Add an AI Column

1. Click + Add column at the right edge of your table.
2. Select AI Column.
3. Choose the AI Column type you want.

Available AI Column types

Text generation

Use this when you want the model to write something new based on your data.

Examples:

• Write a personalized cold email opening line based on a person's job title and company
• Summarize a company's website content into one sentence
• Generate a follow-up reason based on the prospect's LinkedIn headline

How to configure:

1. Write a prompt in the Prompt field. Use {{column_name}} to include column values.
2. Select the AI model (e.g., GPT-4, Claude, or Gemini).
3. Set the maximum response length.
4. Click Save.

Classification

Use this when you want to assign each row to one of a fixed set of categories.

Examples:

• Classify a job title as executive, manager, or individual contributor
• Label industries as tech, healthcare, finance, or other
• Identify whether an email address is personal or work

How to configure:

1. Enter the categories you want to classify into. Add one per line.
2. Write the classification prompt. Include the categories in the prompt.
3. Select the AI model.
4. Click Save.

The output is always one of the categories you defined.

Extraction

Use this when you want to pull a specific piece of information from a longer text.

Examples:

• Extract the company name from a person's LinkedIn headline
• Pull the years of experience from a biography or job description
• Extract the technology stack from a website's scraped content

How to configure:

1. Describe exactly what you want to extract.
2. Specify the expected format (e.g., "Return only the company name as plain text").
3. Select the AI model.
4. Click Save.

Scoring

Use this when you want to assign a numeric score to each row based on criteria you define.

Examples:

• Score each prospect from 1-10 based on their job title and company size
• Rate how relevant a company's description is to your product
• Score email subject line effectiveness based on personalization and length

How to configure:

1. Define the scoring criteria in the prompt.
2. Specify the score range (e.g., 1–10).
3. Instruct the model to return only the numeric score.
4. Select the AI model.
5. Click Save.

Choose the right AI model

Different models trade off speed, cost, and quality:

• Use GPT-4 or Claude for nuanced tasks like scoring or evaluation
• Use GPT-3.5 or Gemini Flash for fast, high-volume classification or extraction tasks where quality requirements are lower

The model selection appears in the column configuration. Switch models at any time.

Credit cost

AI Column credit cost depends on the model selected and the length of the prompt and response. Check the action details panel when configuring the column to see the estimated cost per row.

Troubleshooting

AI Column returns inconsistent results across rows. The prompt is too open-ended. Add specific constraints such as "Return only one word" or list the exact values you accept. Test on 10–20 rows before running on the full table.

The output column contains raw JSON instead of the value I expected. Your prompt is asking the model to return structured JSON. Either parse the JSON using a formula column downstream, or rewrite the prompt to return plain text.

The column returns empty responses for some rows. Check that the input columns referenced in the prompt are not empty for those rows. An empty input often causes the model to skip or return blank output.

I want to use a model not listed in the dropdown. The available models depend on your AI Column configuration. Contact support to inquire about adding a specific model.