Snapshots are a little bit of magic Install them into your agency account and then push them through to a subaccount and you can magically have whole new workflows, forms, web pages and more. But sometimes it can be confusing. There's often a question about whether one snapshot will conflict with another and what will happen. And sadly it is possible if you are getting snapshots from different places. But I wanted to share some details about how I look/think about snapshots when I create them and build my bots. 1. I identify what custom fields and values I need for the bot, like a field for conversation history, or the first message to be sent 2. I create them with a naming structure that reflects the bot like "Reputation Convo History" or "Demo Tool - First Message" 3. I create folders for the custom fields and values 4. I repeat the same process for workflows - separate naming for each bot to minimise conflicts This way, I can have multiple bots installed into the same subaccount for a client without any conflicts. Hope it helps!

With a few recent tweaks and updates I wanted to share this overview video of the demo tool I created. It's make it so much quicker and easier for me to demo conversations on zoom calls without having to get someone to click links, scan QR codes and fiddle with OpenAI Playground. The best part.... It hooks directly into my GHL account and the workflows I'm using with clients. The workflows for Database Reactivation, Speed to Lead AND Reputation bots. And setup involves 4 simple steps; 1. Enter the prospect's company name 2. Enter the bot's name 3. Give a description of their main product or service 4. Select what type of bot to demo Then hit "Save Agent Setup" and it will load the conversation window with a demo contact going into the workflows. Once the conversation is finished I can click "End Conversation" and it will delete the contact and enable me to spin up a new demo conversation/agent type. Here's the video showing it in action!

I am preparing to do a test for a French client. The android works great but when I go to buy a French mobile number for SMS, there are none available. Any ideas? I have also asked the question of GHL but wondered if anyone has already solved this problem?

Can anyone help me with integration of Google Sheets into GHL? I would like to transcribe conversations into google sheets to share with the client... Thanks!

[VIDEO NOW INCLUDED!] Last week I finished a small DBR campaign for a MedSpa in the US and wanted to share some learnings in case they help you with your campaigns. I'll also look to create a video for YT where I'll go into more detail about what I built.. But first.... Learning 1) EMOJI RESPONSES!! 🤣😱 I hadn't even thought about this but when going through testing one of the test users sent "Liked" the SMS from the AI.. And that meant in the conversation history in GHL the user sent back the same message the AI sent.. In the format "Liked {{message from AI}}" You can probably guess what happened?! The AI didn't know how to respond and so repeated the same question or message it sent before Here's what I did to resolve it.... - Created a part in a workflow where I'm recording the responses from the user - Using an IF/ELSE step to detect if the user message started with "Liked" or "Loved" - If it did, then I updated the custom field on the contact record with a manual update like "Yes sounds good" rather than the full contents of the message from the user (which was a repeat of the message from the AI) - If the message from the user didn't contain "Liked" or "Loved" the other branch in the IF/ELSE just updated the conversation as normal Learning 2) AI doesn't like the end of conversations Ever had a situation where you've added into the prompt the message for the AI to send at the end of a conversation and then it seems to get into a loop and repeat itself whenever a user responds? Here's what I did to solve it... - I thought about conversations "states" - like a story, a conversation has a start, middle and end - I created a workflow that uses a ChatGPT step to determine the "intent" of the conversation so far - It outputs a single word - "continue", "closing" or "stop" - That then feeds into an IF/ELSE step - if chatgpt thinks the conversation is mid-flow and outputs "continue" the user goes down a path that adds them to a workflow to create the next AI message in the conversation but if it think's the conversation is "closing" it will send a static message like "hope to see you soon" and then not do anything else