Research Step

Run an AI prompt to reason over lead data, research accounts on the web, and extract structured results.

The Research step runs a custom instruction against an LLM, with the lead's data as context. It can search the web to learn about a lead or their company, then classify leads, generate personalized content, or extract structured information for use in downstream steps.

The Research step configuration panel with instructions, field definitions, and tools.

Configuration

Instructions

Write the prompt that the LLM will execute. Instructions support variables: use the Insert menu (⚡, Variables tab only) to reference lead data fields.

Be specific about what you want the model to produce. If you're extracting structured data, describe the expected output clearly.

Example instruction:

Based on the lead's job title ({{ job_title }}), company size ({{ employee_count }} employees),
and the pages they visited on our website ({{ pages_visited }}), classify their buying intent
as one of: HIGH, MEDIUM, or LOW.

Return only the classification word with no explanation.

Tools

Optionally enable one or both tools to give the LLM access to live information:

Tool	What it does
Web Search	Allows the LLM to search the internet to research the lead or their company
Fetch URL	Allows the LLM to retrieve the contents of a specific URL

These tools are useful for account research steps, for example looking up a company's recent news or fetching their pricing page.

Field Extraction

Save the LLM's output (or parts of it) into lead fields for use in downstream steps. These become available as workflow-scoped variables.

Add one or more Fields:

Field	Description
Name	The field name (e.g., buyer_intent). Use snake_case.
Description	Describe what value should be extracted from the LLM output.

Example: Intent Classification + Personalized Email

1

Research step: classify intent

Instructions:

Review {{ first_name }}'s activity: they work at {{ company_name }} ({{ employee_count }} employees)
as a {{ job_title }} and visited {{ pages_visited }}. Rate their buying intent: HIGH, MEDIUM, or LOW.

Field Extraction:

• Name: buyer_intent
• Description: The intent classification (HIGH, MEDIUM, or LOW)

2

Condition step: branch by intent

• Branch 1: buyer_intent equals HIGH → Call Phone
• Branch 2: buyer_intent equals MEDIUM → Send Email
• Branch 3: (catch-all) → Wait 7 days, then Send Email

3

Send Email step: reference the extracted field

Subject: Following up, {{ first_name }}

Body: Hi {{ first_name }}, based on your interest in our platform...

The email content can vary per branch, using {{ buyer_intent }} if needed.

Tips

Be explicit in instructions. LLMs produce more reliable structured output when you specify the exact format you expect. For classification tasks, provide the list of valid values.

Use Web Search for account research. Enabling Web Search lets the model pull current information about a lead's company (recent funding, news, tech stack) to personalize downstream messaging.