Smart lead capture

A form that doesn't just collect — it qualifies. Every submission is read by an agent, scored, stored, and the right person gets notified.

The pattern

Form Input → LLM Agent (classify & enrich) → Conditional Flow
                                              ├─ hot lead  → CRM + Email (sales)
                                              └─ cold lead → CRM

Step by step

1. Form Input (Public Interfaces) — fields: name, email, company, message. Publish and embed it with Widget.
2. LLM Agent (AI) — objective: "Classify this lead as HOT or COLD for our product. HOT = decision maker, clear need or budget. Extract company size and use case. Answer as JSON: {score, reason, company_size, use_case}." Prompt uses the form variables: {{form_input_1.name}} — {{form_input_1.message}}.
3. Conditional Flow (Base) — branch on the agent's score.
4. HiveApp → CRM (Tools) — both branches register the contact with the enrichment attached.
5. Email (Applications) — hot branch only: notify sales with the reason and use case.

Variations

• Use a Transformer after the LLM to normalize the JSON before branching.
• Swap Email for a Slack/Teams message via an MCP integration.
• Follow with the approval workflow if a human should vet leads before outreach.

Genius prompt: "Create a lead capture flow: public form → AI that classifies hot/cold and enriches → save to CRM → email sales on hot leads."