Table of Contents

Capture, generate and use data with AI Agents

Desirée M Updated by Desirée M

AI Agents aren’t just for answering frequently asked questions — they can also capture information (for example, for lead generation) and generate data based on user conversations.

Store data

The information about the data your AI Agent will capture lives in this section: Store Data.

For example, if your Agent is set up to capture lead information, this is where you decide what data to collect and where it should be saved. To save you time, we've provided some templates!

If you select the “Contact info” template, it will will automatically create fields for phone, email, and name. If you want to delete one of the options, you can easily do it clicking on the three points in the right.

You can also create custom fields from scratch:

Start by choosing where the data should be stored. For example, you could create a Field called “location.”

Then, tell the agent exactly what information to save in this Field (for example, “the user’s location”).

If you’re new to Fields in Landbot, check out this article first: A Guide to Using Fields

Set Up Instructions

To make the agent ask for information, you need to include it in the main Instructions (the prompt).

For example, if it's collecting contact details, or custom information, include that info in the prompt as well:

Important: Be as specific as possible when you explain how the Agent should capture the information. Give clear examples so the Agent knows what to expect and how to store each answer.

If you want budget ranges like 0–100, 101–200, or 201–500, include sample user messages. For example:

• If the user says “22”, the Agent should store “0–100.”

• If the user says “I’m not sure”, instruct the Agent on what it should do (for example, store “Unknown.”)

Prepare for cases where users don’t know the answer or give vague replies.

Offer options and guidance so the Agent captures the information in a consistent way every time.

Generate data from conversation interactions

Besides capturing direct answers, you can also set up your agent to analyze the conversation and create useful insights based on what the user says. For example, you can ask it to identify whether a lead is qualified or not:

Use data outside the AI Agent

Once you capture information, you can use it throughout the chatbot experience. Make sure to use the same field names and data types for consistency.

Was this article helpful?

AI Agent In Action - Live Implementation Example

How to write documents for the AI Agent Knowledge Base

Contact