AI Employee

We tried a lot using prompt or additional instruction to let the AI answer in point form, which is shown in screenshot 3, and it always not working, then we checked the "AI Response Info", we found that the Original Answer composed by AI is exactly what we want, you can see the 1st screenshot, but when the AI answered in the chatbot, it is modified, I think this is done by GHL system, please check the 2nd screenshot. Can we just let the AI ChatBot reply to what the original AI answer is?

Use the new Brand Voice feature as the main guide for all your AI agents. It should be the core reference point they all pull from to stay consistent in tone, language, and messaging. The AI should be able to learn from the info in the Brand Voice on its own. Also, any avatars you create should match the tone and style set by the Brand Voice.

Clients don't like seeing the thought process because, honestly, it makes a lot of mistakes and it's all over the place and it takes a little bit. They don't understand this. Just put "loading" or something on there and give it the final result, or at least give us the option to turn it off.

We are getting automated tags for calls who might be scam, we could have an option if we don't want Voice AI to answer those calls and maybe even put them automatically to Incoming DND list. If the Voice AI recognize that the call is robocall, he should just hang-up and not continue to try to have a conversations with another bot.

We’d love to see this added to your roadmap. After a call or new opportunity is created, the system should be able to review the notes, call transcription, and overall context—and then take action automatically: Create custom follow-up tasks based on what was discussed (next steps, urgency, objections, etc.) Start a drip follow-up sequence (email + SMS) that actually reflects the conversation, not just a generic template Adjust messaging based on the lead’s situation, case type, and level of interest Update or trigger additional follow-up if there’s no response or new activity The goal here is to make follow-up feel more personalized and consistent without relying on the team to manually build everything every time. This would have a big impact on conversion and make sure opportunities don’t fall through the cracks. Happy to share more examples if helpful. Thanks – Philip

It would be good to be able to combine the Voice AI and Conversation (text) together on one app that can be placed as a widget on a website just like the Chat Bot widget is now. Give an option to either talk to an agent or text with an agent.

I'd like to request the ability for AI token usage within HighLevel to authenticate and connect using our existing $20/month personal subscriptions from major AI providers like ChatGPT, Gemini, and Claude — instead of requiring separate API key purchases or GoHighLevel's built-in token credits. This would work similarly to how OpenClaw and VS Code's AI integrations operate: you log in with your existing account (OAuth or session-based authentication), and the platform taps into the token limits you already have from your subscription. This means if I already pay $20/mo for ChatGPT Plus, $20/mo for Gemini Advanced, and $20/mo for Claude Pro, I should be able to leverage those token allowances directly inside HighLevel's AI Employee and other AI features. Current pain point: Right now, agencies and power users have to either pay for separate API access through OpenAI/Anthropic/Google (which charges per token on top of subscriptions), or burn through HighLevel's token credits that come with the platform. This creates unnecessary double-dipping costs. The proposed solution would let users: Connect their existing ChatGPT Plus, Gemini Advanced, and Claude Pro accounts via OAuth/login Have AI Employee and other HL AI features pull from those existing token pools Avoid paying twice — once for the subscription and again for API usage This is a huge value-add for agencies running HighLevel at scale. It reduces operational costs, makes the platform more competitive with tools like OpenClaw, and gives users flexibility to use the AI models they're already paying for. It's the kind of integration that would make HL a no-brainer for agencies already invested in these AI subscriptions.

It’s crazy that in 2025 the AI still can’t send a simple image or PDF. Businesses need to share promos, price lists, menus, or videos, and text alone isn’t enough. Platforms like ManyChat have allowed this for years. If we want AI to really replace human conversations, it must be able to send media files—just like a real agent. 👉 JPG, PDF, MP4 support is essential for modern sales and service.

AI Employee should be able to hand off approved tasks to external AI agents through MCP, webhooks, or custom actions. The goal is not just answering calls or chats. The goal is letting AI Employee operate the business safely. Needed MVP: Send conversation context to an external agent Send contact context Send opportunity context Send calendar context Trigger approved actions Receive results back from the external agent Update the contact Update the opportunity Book or reschedule appointments Add notes Apply tags Trigger workflows Escalate to a human when needed Require approval for sensitive actions Keep full audit logs Example: AI Employee answers a call Customer wants a quote AI Employee sends the task to an approved external agent The agent checks CRM history, calendar, pipeline, and business rules The agent returns the next best action AI Employee books the appointment, updates the opportunity, and sends the owner a summary This would let agencies connect Codex, ChatGPT, Claude, Cursor, OpenClaw, and other AI builders without relying on browser automation. AI Employee becomes the front line worker. External agents become the back office operators.

A true AI Receptionist needs to be able to take a phone message that gets sent to the appropriate employee or transfer a caller to their voicemail on the platform.