---
title: "Table Read Agent"
description: "EMILY.RPA Table Read Agent module: use a large language model to extract information from spreadsheets into the working folder."
source: https://docs.emily.tips/en/ai-agent/table-read-agent
---

# Table Read Agent

Table Read Agent uses a large language model (LLM) to extract information from spreadsheets and outputs the results to files in the working folder. If you're unfamiliar with how to prompt the language model to achieve task goals, use "**Ask EMILY**" to let the AI generate model-friendly goal prompts.

![](https://docs.emily.tips/img/en/ai-agent-061.png)

## Parameters

**`API KEY`** - OpenAI or Google API key. Supports the **%FILENAME%** variable, or use the prepaid dedicated key **%credit-key%**.

* For OpenAI API Key, refer to [Apply for OpenAI Key](/faq/apply-openai-key)
* For Google API Key, refer to [Apply for Gemini Key](/faq/apply-gemini-key)

**`MODEL`** - Currently supported models:

| Platform | Models                                                          | Pricing                                                 | 
| -------- | --------------------------------------------------------------- | ------------------------------------------------------- |
| OpenAI   | gtp-5, gpt-5-mini, gpt-4.1, gpt-4.1-mini                       | [OpenAI Website](https://platform.openai.com/docs/models) |
| Google    | gemini-3-pro, gemini-3-flash, gemini-2.5-pro, gemini-2.5-flash | [Gemini Website](https://ai.google.dev/gemini-api/docs/pricing) |
| Anthropic | claude-opus-4-6, claude-sonnet-4-6, claude-haiku-4-5             | [Anthropic Website](https://docs.anthropic.com/en/docs/about-claude/models) |

**`XLSX/CSV/TSV/GOOGLESHEET`** - Input file. Click "**PICK**" to select a file, or use the **%FILENAME%** variable. In addition to the listed file formats, **Google Sheets ID** is also supported.

**`SHEET`** - Enter the worksheet name. Leave empty to use the first worksheet in the file.

### ADD PROMPT

Add a natural language prompt to tell the model what information to extract from the spreadsheet. **`FILENAME`** specifies the file to write to in the working folder. **`PROMPT`** tells the model what information to extract from the spreadsheet.

![](https://docs.emily.tips/img/en/ai-agent-062.png)

## Example

Using the following sales records table as an example, the goal is to find transactions with a total amount greater than 50,000.

![](https://docs.emily.tips/img/en/ai-agent-063.png)

For the Table Read Agent, select the model `Google/gemini-2.5-flash` and add a prompt with filename `high_value_sales.txt` and prompt: Find all records where the total amount is greater than 500...

![](https://docs.emily.tips/img/en/ai-agent-064.png)

Finally, click "**TEST**" to try it out, then check whether the content of `high_value_sales.txt` in the working folder is correct.

![](https://docs.emily.tips/img/en/ai-agent-065.png)