Turn your website chat into a lead capture and scoring system

A website chatbot answers visitor questions, captures their contact info, and scores each lead automatically.

How the work actually flows

It branches. Exactly one path is taken; runs once per each inactive conversation.

Pattern: Exclusive Choice (4) · Simple Merge (5) · Multiple Instances with a priori Design-Time Knowledge (13)

flowchart TD trig>"visitor starts website chat"]:::trig s0(("capture visitor contact info")):::human s1["ai answers from knowledge base"]:::svc s2[("save contact and match lead")]:::store s3[["score inactive conversations"]]:::mi trig --> s0 s0 --> s1 s2 -->|"one per each inactive conversation"| s3 gx{"× does message mention pricing or urgency"}:::gate s1 --> gx p00["alert team in slack"]:::task gx -->|"pricing or urgency mentioned"| p00 p10["continue conversation"]:::task gx -->|"routine question"| p10 jn{"○ save contact details"}:::gate p00 --> jn p10 --> jn jn --> s2 out[/"leads scored hot warm or cold"/]:::out pay{{"captures and qualifies leads automatically"}}:::pay s3 --> out out --> pay classDef task fill:#e7f6fe,stroke:#34b8f0,color:#2c2a29 classDef svc fill:#f6f8fa,stroke:#7c8795,color:#2c2a29 classDef mi fill:#e7f6fe,stroke:#0079a8,color:#2c2a29,stroke-width:2px classDef human fill:#fff,stroke:#0079a8,color:#0079a8 classDef store fill:#f6f8fa,stroke:#0079a8,color:#2c2a29 classDef trig fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigtime fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigdata fill:#8ad4f5,stroke:#0079a8,color:#06314c,font-weight:bold classDef gate fill:#fff,stroke:#e8a23d,color:#6b4708,font-weight:bold classDef out fill:#1f9d6b,stroke:#167a53,color:#fff,font-weight:bold classDef pay fill:#06314c,stroke:#021f33,color:#fff
Starts itAn outside serviceRuns once per itemA personA record or sheetOne path onlyPaths rejoinResultPayoff
Build size
Advanced

A larger build with multiple systems, AI reasoning, and custom rules.

Business functions
AI Agents & Autonomous SystemsAI Chatbots & AssistantsKnowledge Base & RAGMessaging & NotificationsSpreadsheet & Database Ops
Connects
Google GeminiSupabaseCohereGoogle SheetsSlack

The problem it solves

Visitors land on your site with real questions, but if nobody's watching the chat you lose them before you ever get a name or email. And even when you do capture a lead, figuring out who's actually ready to buy means digging through conversation logs by hand.

Who it fits

Good for B2B or service businesses that want their website chat to double as a lead qualification tool.

How it works

  1. A visitor starts a chat on your website and is asked for their name and email before getting answers
  2. The AI answers their questions using your own knowledge base
  3. Their contact details and conversation are saved, matching them to existing leads if they've chatted before
  4. When someone asks about pricing or shows urgency, your team gets a Slack alert
  5. Every 10 minutes, inactive conversations are scored 1 to 10 and marked hot, warm, or cold in Google Sheets
What you get

Chats that turn into real qualified conversations

Every website visitor gets an instant, knowledgeable answer while your team is alerted the moment a lead looks ready to buy.

What you get

A running list of leads in Google Sheets with contact info, conversation notes, and a hot, warm, or cold score.

What you need

A Supabase account, a Google Gemini API key, a Cohere API key, a Slack account, and a Google Sheets account.

We can build this. But should you?

The hard question is not how to build it. It is whether this is the right thing to build first.

That is what a Fractional Chief AI Officer figures out with you, before anyone writes a line of code.

Let's Talk Strategy

Related automations

Back to the AI Playbook