Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
637 contributions to AI Automation Agency Ninjas
Multiple AI Agent versions
Anyone running multiple AI agents (or one agent with different personas) in a single GHL sub-account? I have a client with an existing agent geared towards fishing and boat rental, and I’m adding hunting and birding campaigns. I need leads routed to a different agent or knowledge set based on which Meta form they came from, so hunters never hear about birding and vice versa. Is that done with separate agents triggered by tags, or one agent reading a custom field? Any gotchas with two agents fighting over the same conversation?
1 like • 12h
One agent, one webhook, routed by a custom field. The snapshot already ships the field for it: **Active Agent** (`{{contact.active_agent}}`), a single-option dropdown. Set it on entry from the Meta form (each form gets its own tag plus its own Active Agent value), pass it to your n8n/Make scenario, and switch the system prompt and knowledge set on that value. Duplicating the whole workflow per persona triples your maintenance and is where the fights start. Gotchas worth planning for now: 1. **Two published start workflows is the classic double-send.** If you clone `0 - Start GPT` per niche, a contact who fills two forms enters both and you get two replies to one inbound SMS. One entry workflow, branch inside it. 2. **Same phone number, one conversation thread.** A returning contact keeps their old history. Decide the rule: either Active Agent is sticky (first one wins) or it gets overwritten on new form fill. Overwriting mid-conversation is what makes a bot answer a fishing question with birding copy. 3. **Chat history is shared.** `Grab Chat History` pulls the whole thread, so the hunting agent will read the fishing conversation. Either filter history by the campaign or instruct the prompt to only act on the current enquiry. 4. **Calendar and bumps.** Bump SMS 1/2/3 are single custom values. If the personas need different nudges, move that copy into your automation rather than the custom values. Set Active Agent as the very first action on form entry, before the AI ever fires, and most of this never surfaces.
Transfer a lead to a live agent?
Can Sales Wingman take a hot lead or a live call and transfer them to a live agent on the phone?
1 like • 2d
Worth separating two things here. Sales Wingman Lite is a demo tool: it exists so a prospect can chat with your AI or ring the voice agent and see it work while you watch the transcript live. It is not the production agent that runs your client's phone line, so live transfer to a human is not what it is built for. Where you do want warm transfer is in the actual deployment. In practice that means a voice agent (Vapi, Retell, Synthflow, or HighLevel's own voice setup) with a transfer action on the agent, triggered when the lead hits your qualification criteria. The agent says "let me put you through", dials the sales line, and bridges the call. If nobody picks up, fall back to booking an appointment so the lead never dead ends. Dan builds one end to end here: https://www.youtube.com/watch?v=JeamqojHUHc For SMS Androids there is no transfer as such, you just hand off in the pipeline and alert the human.
Where did you hire your callers?
Anyone successful at hiring callers, wich channel are you using to find them?
1 like • 3d
For callers, the two channels that actually work are OnlineJobs.ph for Filipino appointment setters and Upwork for native English when the niche needs it. Facebook groups for sales reps are a third option but the quality is wild. What matters more than the channel is how you filter: 1. Post the role with the pay and the KPI in the ad, not "commission only". Commission only gets you people who quit in week two. 2. Make every applicant send a 60 second voice recording reading your actual script. You will cut 80% on tone alone. 3. Paid trial day on real leads, not a mock call. You find out in an hour whether they can handle a "not interested". 4. Give them a tight script and one objective (book the appointment), not freedom to sell. Worth asking yourself first whether you need a caller at all. If the AI is booking and you just need someone to show up to calls, that is a different, cheaper hire.
Claude vs Open AI
Hi Is anyone using Claude instead of Open AI for Sleeping Beauty? Does it matter which one you use?
0 likes • 5d
It doesn't really matter. The Android doesn't care which model sits behind the webhook, it just needs a reply written back into the Chat-GPT custom field. Swap the model node in n8n/Make/Zapier and everything else stays as it is. Practical differences worth knowing: 1. Claude tends to follow a long system prompt more tightly and is less likely to drift out of character or over-explain. Good for SMS where you want short, human replies. 2. OpenAI has more examples floating around, so if you're copying a build from a video the nodes will line up with less fiddling. 3. Whichever you pick, watch message length. Models love writing paragraphs, and every 160 characters is another billed segment. Put a hard "keep replies under X characters" instruction in the prompt and test it. One thing you must add either way: an instruction that if the lead asks whether they're talking to a bot, it answers honestly and immediately that it's an AI. Most prompts tell the bot to stay in character no matter what, and that's the bit that breaks under the EU AI Act if any of your contacts sit in the EU (Ireland catches a lot of UK people out). Dan covers it here: https://www.youtube.com/watch?v=ZWqcUUbqDb4
Database reactivation for Attorneys
I have a potential client who is an attorney that is interested in database reactivation SMS. Laws prohibit getting revenue or profit share for attorneys. Cost per action is OK or a monthly retainer is OK Attorney is criminal defense and personal injury. I am looking for pricing ideas.
2 likes • 7d
Legal is one of the few niches where you genuinely can't do rev share, so price off case value instead. For criminal defence and PI, a signed case is worth thousands to tens of thousands, so a per-qualified-consultation or per-signed-case fee is easy to justify. How I'd structure it: 1. Setup fee, 1,000 to 2,500, covers the build, A2P registration, list clean, prompt and the first campaign. Never do the build free. 2. Then either a flat monthly retainer, or a per-booked-consultation fee. Retainer is simpler to get approved by their compliance and easier for you to forecast. 3. Make them pay the usage directly, or build it in with headroom. A 2,000 lead campaign runs about 130 in SMS, so price well above that. Two practical points. Old PI and criminal leads need consent checking before you text them, and the firm must confirm they have it, in writing. Also keep the AI off anything that reads as legal advice or a case outcome promise, that is a bar rule problem for them, not just a conversion one. Ask them for their average case value on the first call, every number above hangs off it.
1-10 of 637
Graham Connolly
6
1,370 points to level up
@graham-connolly
Paid Ads & Marketing Automation Expert

Active 16h ago
Joined Jun 27, 2023
ENTP
Powered by