AI Employee

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.

Separate the options for the AI Employee to stop when I send a message from when a workflow is activated. For example, I want it to stop when I intervene in the conversation, but not when a workflow for sending images is activated.

When a domain has already been crawled, the daily crawl should automatically detect any new pages that have been added to that domain and include them in the knowledge base, rather than only re-crawling the existing pages. If automatically adding new pages isn't possible, the daily crawl should at least identify and display any newly discovered pages at the top of the crawl results, with a simple option to add them to the knowledge base.

SEVERITY: CRITICAL — Real business damage, live campaign failure, full day of lost work SUMMARY: The AI in the AI Studio / vibe coding platform repeatedly and confidently confirmed that a quiz sequence it helped build would port results directly into the CRM. This was factually incorrect — it cannot do this. The false confirmation was given multiple times across multiple checkpoints in the conversation, leading the user to trust and deploy the quiz as part of a live marketing campaign. WHAT HAPPENED: Used AI Studio to build a quiz sequence Explicitly asked the AI multiple times whether quiz results would sync/port to the CRM AI confirmed YES each time — clearly and without caveat Quiz was QA tested, client-reviewed, and launched as part of a live campaign Results did not appear in the CRM — because the AI cannot actually do this User spent an entire day troubleshooting before discovering the AI's capability claims were false The entire quiz had to be rebuilt from scratch in a different tool while the campaign was already live WHY THIS IS CRITICAL: The AI is actively misrepresenting its own capabilities to users Users cannot distinguish between what the AI CAN do vs. what it THINKS it can do This is not a minor UX bug — it caused real, documented business damage to a live client campaign Any other agency or user who asks the AI the same question will receive the same false confirmation This creates serious trust and liability issues for GHL as a platform REQUESTED ACTION: Immediately audit what the AI Studio AI claims it can and cannot do re: CRM data sync Add hard guardrails so the AI cannot confirm capabilities that do not exist If CRM result porting is not supported, the AI must clearly say so — every time Consider adding a warning/disclaimer in AI Studio about what integrations are and are not supported This was described by the affected agency owner as one of the worst experiences in their entire marketing career, caused entirely by trusting the platform's own AI assistant.

Why is everything with Services V2 always overlooked? I really can't understand this. Do you guys work in the same building? Ask AI cannot find anything related to the Services V2 calendars. This is a huge problem. Please, this needs to get done quickly and not wait over a year to add it to things like conversational AI.

Example: Hair Salon enables Voice AI for overnight calls (from 5pm to 8am) There are 2 hair dressers available on the booking calendar, each with 1 hour time slots If 1 is booked 2-3pm, still leave Voice AI disabled because that time slot is not fully booked But if both are booked from 2-3pm, then auto-enable Voice AI to answer the phone, including before and after buffer times... So Voice AI takes over from 1:45pm-3:10pm... without having to manually for this time slot

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?

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.

Financial debts, time, negligence

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.