Using Extractions to Populate Custom Fields

Introduction

This guide walks you through how to extract important information from conversations using tools and sync that data into custom fields in GoHighLevel. We'll cover how to create and connect extractions, how to prompt for them, and where that data ends up.

1. Set Up Extraction Tools

• Go to the right-hand sidebar and click Tools and Abilities.
• Select Manage Tools → scroll to Extraction.
• Click Create a Tool and choose Extraction as the type.
• Name your tool (e.g., extract_user_business_name).
• Use lowercase and underscores — avoid spaces. It must follow JSON formatting.
• Paste in the extraction description (example below).

Example Description:
“Always use this tool to extract and store the user's business name so a team member can reference the information at a later date.”

2. Map the Tool to a Custom Field

• You must create custom fields in GoHighLevel before syncing tools.
• Once created, search your field (e.g., “Business Name”) when prompted in the tool setup.
• Click to sync it with the extraction tool.

3. Repeat for Each Data Point

You can create similar tools for:

• Business Description
• Best Selling Service
• Session Feedback

Use the same structure and formatting for each. Add them all to your assistant after setup.

4. Add Extractions to the Prompt

It’s not required to prompt every extraction, but doing so improves consistency. Here’s how you should prompt it inside your task list:

Example Prompt Snippets:

• Step 5 (Business Name):
  “Use the tool extract_user_business_name to extract and store the user's business name. This is an internal tool, so don’t mention it to the user. Continue to step 6 after calling the tool.”
• Step 7 (Business Description):
  “Call the tool extract_user_business_description to extract and store the user's description. Do not use the tool output in your response. Move to step 8 afterward.”
• Step 9 (Best Selling Service):
  “Call the tool extract_user_service to extract and store the user's best-selling service. Do not include tool responses in chat. Proceed to step 10.”
• Step 13 (Session Feedback):
  “Call the tool extract_user_feedback to extract and store session feedback from step 12. This is internal. Move to step 14 afterward.”

5. Notes on Using Tools in Prompts

• These tools are invisible to the user unless you include their output in the assistant’s response.
• Use phrasing like “move to step X after calling the tool” to maintain flow and keep the tool call silent.
• If you're using external tools (e.g., via Make, Buildship), you can return dynamic values and display them if desired.

6. Final Custom Field Sync & Location

• Once synced, all extracted data will be stored in the mapped custom field.
• You can view this data inside the contact record in GoHighLevel.
• Custom fields used in the demo: Business Name, Business Description, Best Selling Service, Session Feedback.

Tips

• Create and name your custom fields before setting up extraction tools.
• Use internal phrasing to keep tool calls hidden from the user.
• Prompting the assistant to use tools increases accuracy.
• Always add tools to the assistant after setup — otherwise they won’t be used.

Summary

This guide shows how to extract user data like business name, service, and feedback into custom fields using extraction tools. You create tools, sync them to fields, and guide the assistant through prompts to call those tools invisibly during conversation. Everything syncs seamlessly into GoHighLevel for your team to use later.

• Create extraction tools in Tools & Abilities.
• Use JSON formatting and connect each to a custom field.
• Prompt tool usage in your assistant's task list.
• Add the tools to your assistant after setup.
• All data goes directly into your GoHighLevel contact record.