Icon

02 Data-aware Agent

<p>This workflow demonstrates how to create an agent that can process <strong>a table </strong>containing product feedback. The agent is able to send the table to various tools and return the updated table in its second output port. In the <strong>conversation</strong> you can see the reasoning behind the tool choices and the results generated by each tool.</p>

This workflow demonstrates how to create an agent that can process a table containing product feedback. The agent is able to send the table to various tools and return the updated table in its second output port. In the conversation you can see the reasoning behind the tool choices and the results generated by each tool.

Set up the OpenAI API key, authenticate, and select the LLM

02 Data-aware Agent

This workflow demonstrates how to create an agent that can process a table containing product feedback. The agent is able to send the table to various tools and return the updated table in its second output port. In the conversation you can see the reasoning behind the tool choices and the results generated by each tool.

List the tools in the Tools-data folder

Table of product feedback

Questions for the agent

The agent can send the input data to the tool which can process and/or visualise it.

Try the following requests:

  • Extract the products mentioned in the input table.

  • Show me the input table.

  • Generate a discount code for the products mentioned in the feedback

Note: the data is not sent to the LLM provider. The agent can only access table specs (table description, column names and column types) and send it to the tools, without accessing its content.

Tools-data
List Files/Folders
Product feedback
Table Creator
Select the model
OpenAI LLM Selector
Authenticate
OpenAI Authenticator
Add your credentials here
Credentials Configuration
Agent Chat Widget (experimental)
Workflow to Tool
First output: conversationSecond output: feedback with discount code
Agent Prompter

Nodes

Extensions

Links