1. Ema v2 Docs
  2. Templates
  3. Lead Qualification AI Employee

Lead Qualification AI Employee

The Lead Qualification AI Employee is built from the Lead Qualification curated template (category: Marketing). It is a form AI Employee (AIE): you submit an intake form, and it extracts structured lead information, then scores the lead against configurable business rules and classifies it as Hot, Warm, or Cold. It eliminates manual lead triage and ensures consistent scoring against your ideal customer profile, so high-value prospects reach sales immediately.

Workflow

The template ships a two-agent workflow that runs left to right:

NodeAgent typeWhat it does
Extract Lead DataextractionPulls structured lead information from the intake submission — company name, size, industry, budget range, timeline, pain points, and contact details — into a defined output schema.
Score & Qualifyrule_validationApplies your lead-scoring rules to the extracted data, sums the points, and classifies the lead as Hot (80+), Warm (50–79), or Cold (<50).

A start node feeds the intake submission into the graph, and a publish node exposes the qualified lead. The edges run start → extract → score → publish.

The Extract Lead Data node ships with an output schema in its type_config. For example:

{
  "output_schema": {
    "type": "object",
    "properties": {
      "company_name":  { "type": "string", "description": "Name of the company" },
      "company_size":  { "type": "string", "description": "Size category: enterprise, mid-market, or SMB" },
      "industry":      { "type": "string", "description": "Industry vertical" },
      "budget_range":  { "type": "string", "description": "Budget range: high, medium, or low" },
      "timeline":      { "type": "string", "description": "Purchase timeline: immediate, this_quarter, or exploring" },
      "pain_points":   { "type": "array", "items": { "type": "string" } },
      "contact_name":  { "type": "string" },
      "contact_email": { "type": "string" }
    },
    "required": ["company_name", "company_size", "budget_range", "timeline"]
  }
}

The Score & Qualify node ships with its scoring rules pre-filled in type_config. For example:

{
  "rules": {
    "operator": "AND",
    "conditions": [
      { "rule": "If company_size is enterprise, assign 30 points; mid-market = 20 points; SMB = 10 points" },
      { "rule": "If timeline is immediate, assign 30 points; this_quarter = 20 points; exploring = 10 points" },
      { "rule": "If budget_range is high, assign 40 points; medium = 25 points; low = 10 points" },
      { "rule": "Sum all points. Classify as Hot if >= 80, Warm if 50-79, Cold if < 50" },
      { "rule": "All required fields (company_name, company_size, budget_range, timeline) must be present" }
    ]
  }
}

Starting configuration

The template clones in with this configuration, which you can change in the builder:

  • Model selection — Let Fusion Pick (EmaFusion™ chooses the model per request).
  • Optimization priority — Balanced.
  • Conversation context — disabled (this is a single-submission form workflow, not a chat).
  • Feedback — enabled, with thumbs-up / thumbs-down reasons and free-text comments.

Recommended data sources: connect your ideal customer profile documentation and lead-scoring criteria so the agent can qualify leads accurately.

How to use

After you select Use template and the AI Employee opens in the builder:

  1. Customize the extraction fields. Edit the output schema in the Extract Lead Data node to match the fields on your intake form.
  2. Adjust the scoring rules. Edit the rules and thresholds in the Score & Qualify node to match your ideal customer profile.
  3. Connect your CRM. Add Tools to push qualified leads into your CRM and tag them by score. See Tools.
  4. Publish and submit. Publish the workflow, then submit intake data and receive the extracted fields with a Hot / Warm / Cold classification.

The scoring rules are expressed in plain language inside the Rule Validator's type_config. Adjust point values and the Hot / Warm / Cold thresholds to match your ICP, then run a few known-good and known-bad leads through to confirm the classifications land where you expect.

Example inputs

  • "Acme Corp, 4,000 employees, healthcare, evaluating now, large budget approved. Pain point: manual claims triage."
  • "Two-person startup, exploring options for next year, no budget yet, curious about pricing."

Last updated: Jul 3, 2026