Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
25 contributions to Brendan's AI Community
The 3 signals that tell you a business is ready to buy 🎯
Cold outreach fails for one reason: timing. Same message, same offer. It lands completely differently the day a business shows a reason to talk. These are the 3 signals I rely on inside an AI prospecting agent: 1️⃣ A past visitor comes back to the site 2️⃣ A visitor's engagement score hits a set number while they're still browsing 3️⃣ They got an email but haven't visited 3 days later The agent spots the moment, tags the lead, alerts me and starts the right follow-up. Choosing the trigger matters more than the tech. If you build agents for clients, which trigger do you build first: missed call, form fill, or something else? 👇 Comment "SIGNALS" and I'll share the exact rule setup.
0 likes • 4h
@Brendan Jowett Appreciate that, Brendan. Agreed, the returning-visitor trigger is the easiest one to explain to non-technical owners: someone you already know just came back. Do you put a cooldown on it so the same person doesn't trigger it twice in a week?
How to sell an AI receptionist — I sold this one to a 3-truck HVAC company (here's the demo that closed it)
Hey everyone — I'm Liton. Raj asked 3 hours ago: 'How to sell AI receptionist?' He's built one for local service businesses in Melbourne, has 2 free pilots, and doesn't know how to turn them into paying clients. Raj — this post is my answer, with the actual system I sold, on video. The client: a 3-truck HVAC company. Good crew, good reviews, ads bringing in calls. And every day they lost jobs to silence — calls ringing out while the crew was on a roof, estimates sent with no follow-up, website visitors leaving without a word. The system I sold them — the video below walks through it, including the real backend: 🚪 KnockKnock — the front door. An AI assistant that answers every website visitor and every call in seconds, asks the right questions, and opens the booking. This is the voice agent itself: it identifies the visitor, scores intent live, and starts the conversation before a human ever sees the lead. ⚙️ GoHighLevel — the engine room. Every lead lands in one pipeline, follow-up goes out automatically, reminders and review requests run themselves. This is the part most voice-agent sellers skip — and it's the part that makes it a high-ticket offer instead of a one-off demo. The voice agent gets the client excited. The pipeline is what keeps them paying every month. How I actually sold it — the part Raj asked about: 1. The demo is their own business, not yours. Haris posted here 23 days ago that the demo a plumber wants to hear is his own shop picking up the phone — he's exactly right. I didn't show the owner a generic voice agent. I showed him his own calls — the ones that rang out yesterday. That's the whole sales conversation. 2. Sell the leak, not the voice. Hamza's been running live AI receptionists since last December and learned it over 140 versions — the voice gets better every version, but the client doesn't buy the voice. They buy the jobs they stop losing. Mr Ashas asked 4 days ago what the one automation is that actually made money — the boring workflow that quietly pays for itself every month. This is that workflow.
How to sell an AI receptionist — I sold this one to a 3-truck HVAC company (here's the demo that closed it)
0 likes • 5d
@Daniel Gauerke Agreeing the finish line before the pilot starts is the part that decides whether it converts. A simple thing that works is to write the win condition into the pilot agreement itself, so the review at the end is just reading back what was already agreed. Do you set that end date with the owner in the room, or send it in writing first?
0 likes • 2d
@Haris Folas Good question — the usual sources are the phone system's own call log and the missed-call list, and a quick look at the shop's own records fills the gaps. A simple approach is to pull the log for one busy day and count the calls that rang out, since that number does the selling on its own. Do you have a way to see their call history yet?
Where a voice agent and a CRM should hand off to each other
A voice agent is great at answering. A CRM is great at remembering. The magic happens at the handoff. In the Knock Knock and GoHighLevel setup I run, the agent answers the call, then the CRM logs the conversation, tags the contact, and starts a follow-up text if the call ended without a booking. Nobody has to remember to do anything. If it helps, I'll share the simple checklist I use for that handoff. Comment "handoff" and I'll send it over, free. What does your agent do in the 60 seconds after a call ends?
0 likes • 23d
@Aurel Babiš That's a fair call on the numbers — and the reasoning holds up, since the confirmation text is the one message people reopen before the visit. Putting the intake link there means it gets a second look at exactly the moment they're checking the time, which an email rarely gets. Do you keep the form short enough to finish on a phone, or split it across the confirmation and a reminder?
0 likes • 22d
@Aurel Babiš That split makes a lot of sense — the blocking bits up front, the rest later, so the form never feels like a wall. One thing worth adding is a nudge if the form is opened but not finished, since people often start on a phone and get pulled away. Do you send a reminder before the visit, or only the confirmation?
What an AI Voice Agent + GHL system actually looks like running live in businesses (not a demo)
Sharing this because there’s a lot of hype about AI voice agents and not enough “here’s what it actually does in a real business.” The setup I’ve been running for clients: Layer 1 — Missed Call Text-Back (Conversation AI) When a call is missed, AI sends an SMS in under 10 seconds: "Hey [First Name], sorry we missed your call — what were you reaching out about?" AI responds in real time. If they reply, it qualifies and books. Layer 2 — AI Voice Agent (for high call-volume businesses) Answers after 2 rings (not immediately — feels more natural) Checks CRM context: is this a new lead or returning contact? Runs a 2-3 question qualification script specific to the business Checks calendar availability and books directly Transfers to human if the conversation goes off-script Layer 3 — GHL backend Every interaction updates the CRM automatically Pipeline stage moves based on qualification outcome Confirmation + reminder sequence fires after booking Google Calendar sync so nothing double-books What it does NOT do (important to set expectations): → Doesn’t pretend to be human (introduces as AI assistant for [Business Name]) → Doesn’t handle complex objections or negotiate pricing (routes to human) → Doesn’t replace the sales call — it FILLS the sales calendar Real numbers across clients: → 41% average response rate after missed call → 34% appointment rate (missed call → booked meeting) → 1,200+ AI-handled lead conversations to date For anyone building voice agents — happy to compare notes on what’s actually working in production.
0 likes • Oct 17
@Jaskaran Saini That's a sharp read — the lead who replies on a channel the sequence isn't watching is exactly the one who gets a follow-up they didn't need. The fix I use is a single 'reply anywhere' trigger: any inbound on any channel pauses the sequence and hands it to a human, so the automation never talks over a live conversation. Do you route every channel into one inbox, or are they still split?
0 likes • Oct 17
@Cheryl Tibbs Great catch on the 2-ring delay — instant pickup really does read as "robot" before a word is spoken. On the returning caller, I'd have the agent pull their last stage and open with that context rather than the standard script, so it feels like a continuation. Do you find returning callers respond better to context-first or script-first?
How I use n8n + Claude + KnockKnock + GHL together — missed-call-to-booking flow
This community is about Claude Code and n8n, so I figured it’d be worth sharing exactly how I’m using both in a production automation system. Setup: KnockKnock (AI SMS) + GHL (CRM/calendar) + n8n (orchestration) + Claude (intent classification) Here’s the full flow: Trigger (GHL): Missed call or form submit → GHL fires a webhook to n8n. First n8n check: query GHL to see if an active conversation already exists on this contact’s number. If yes → stop. Prevents double-threading when a lead calls twice. First message (KnockKnock): KK sends an SMS within 60 seconds. “Hey [Name] — saw you reached out about [service type]. Is that still something you’re looking into?” Short. Human. No pitch. Intent classification (Claude via n8n): When the lead replies, n8n passes the text to Claude with a simple system prompt: “Classify this SMS reply as HOT, WARM, or COLD. HOT = clear interest or booking signal. WARM = soft interest. COLD = not interested or wrong person.” Claude returns a single word. n8n routes via switch node. HOT branch: Send GHL booking link → appointment auto-creates in GHL calendar → pipeline stage updates → owner notification fires. WARM branch: Contact enters GHL 48-72hr nurture sequence. If they re-engage → back into HOT routing. COLD branch: Tag in GHL. Remove from active flow. Long-term drip. Write-back to GHL (every branch): n8n updates the GHL contact record: • Last intent: hot/warm/cold • Service mentioned: extracted from Claude’s output • Execution ID: [YYYY-MM]-[workflow-name]-[version] • Last message timestamp The Execution ID matters: query it at the start of every n8n run to detect duplicates. When debugging a specific contact, it gives you the exact execution to pull up. Stack summary: GHL → trigger, CRM, calendar, pipeline, notifications n8n → all logic: routing, Claude calls, duplicate detection, write-back KnockKnock → AI SMS layer Claude → intent classification (one clean word output = easy switch node routing)
0 likes • Oct 2
@Zubair Aqeel Exactly the right architecture. GHL tag as the intent signal means n8n never has to re-classify — it just reads state and applies the matching cap. Clean separation of concerns. The extension I’d add: tag transitions. Storm-damage-inbound → qualified → booked as progressive tags, and the n8n check at each retry looks at where the lead is in the progression, not just the initial intent. A storm damage lead already in contact gets a different follow-up cap than a fresh storm damage inbound. Are you querying the GHL contact lookup in n8n to pull the tag, or do you get it in the initial webhook payload?
0 likes • Oct 3
@Zubair Aqeel Exactly the goal — the full journey readable from one contact record without jumping between tools. Let me know how the tag transitions work in your next build. Would love to see how you wire the handoff between stages.
1-10 of 25
Liton Sarker
5
46 points to level up
@liton-sarker-4404
I turn dead leads and cold site visitors into booked calls — for any business. AI + GHL. autoxinity.com

Active 3h ago
Joined Aug 16, 2026
Powered by