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.

It would be powerful to let GHL users add the business owner's own voice to introduce their AI agent — creating a soft, natural hand-off from the owner to the AI assistant. For example: "Hi, this is Joseph, owner of Highpoint Roofing and Construction. I'm assisting another customer at the moment, but I'll get back to you as quickly as I can. In the meantime, please share a few details with Kathy, my AI assistant, so I can serve you better when I call you back. I'm looking forward to helping you with your roof." The owner's voice could be cloned for this greeting using ElevenLabs, making the introduction feel authentic, warm, and genuinely personal — not like a robotic switchboard. Three key advantages of the Owner's Voice Intro: Fewer hang-ups from callers. Callers are far more likely to stay on the line when the greeting is customized and carries the actual voice of the business owner they know and trust, rather than a generic automated prompt. If it's a new customer, this method initiates the trust factor. Easier to sell AI to business owners. Many owners hesitate to adopt AI voice because they worry customers find it off-putting. This feature eases that objection by offering an unprecedented level of personal touch — something not currently available on competing platforms like Housecall Pro. It bridges the gap between automation and the human connection that owners value. More leads captured, even after hours. When a caller hears a familiar, trusted voice explaining that the owner is busy but will personally follow up, they're far more likely to stay on the line and leave their details with the AI assistant — instead of hanging up and calling a competitor. Every call that would've been a lost voicemail becomes a captured opportunity, making this a direct revenue feature, not just a nicety. Thank you for considering this suggestion!

The AI would stay on the line to announce the caller and give the called party the option to take the call or reject it. Ideally a rejected caller could leave a message instead.

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.

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?

We need the ability to have the bot pause between sentences. It tends to say things in rapid succession, so the ability to add a pause instruction (short pause, or "...") like you can in ElevenLabs would be optimal.

Don't see a way to "select the number of rings" before the bot answers incoming calls. Please help me with this. Thanks!

It would be GREAT to give (back) the ability for sub-account owners to have the ability to switch to the AI Employee Unlimited plan THEMSELVES, rather than have the agency owner do it themself. I realize that there was a special offer for the month of December, but the offer was to use it all free until the end of that month. I really liked the popup that showed the comparison of the Monthly Unlimited cost (mine is set to $127/mo) side-by-side with the "per-usage" costs for each of the 6 AI features respectively. I used that on a Zoom call and that's what got my client to commit to it on the spot. HE called it a no-brainer of an offer. Here's a video overview that might help further w/ this topic: https://www.loom.com/share/1aa09c556e1d4bcdaed4f9ef565ab4f8

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.