Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
4 contributions to AI Automation Society
🚀 Built a Real Estate AI Voice Agent Inside GoHighLevel
I’ve been working on a real estate AI voice agent, and I’ve now built the core system entirely inside GoHighLevel. The agent can currently: 📞 Handle inbound calls 📅 Check calendar availability ✅ Book appointments 🔄 Reschedule appointments ❌ Cancel appointments 🗓️ Manage appointments through the GHL calendar 📝 Collect information from callers What I like about this build is that I didn’t rely on a separate n8n workflow or external voice-agent platform. The whole agent is built inside GHL using its AI voice capabilities, functions, and calendar. The goal is to create something a real estate agency could actually deploy to handle incoming calls and appointment management automatically. Now that the core is working, I’m thinking about what to add next. What feature would you add to make this agent more valuable for a real estate business? Would love to hear your ideas 👇
🚀 Built a Real Estate AI Voice Agent Inside GoHighLevel
4 likes • Aug 15
Nice build. I’d add a short summary after every call with the contact details, reason for calling and agreed next step. That would make it much easier for the team to follow up without listening to the full recording or checking several places.
🚀New Video: I Made Codex and Claude Code Build the Same App. One Clearly Won.
I gave Claude Code and Codex the exact same prompt to build a production-ready Typeform alternative, then compared the products, costs, speed, agent usage, and testing. Claude Code built the more usable app in a fraction of the time, while Codex went much deeper on architecture and reliability. This experiment made it much clearer where each tool fits in my workflow and why the way you prompt them matters.
7 likes • Aug 14
My takeaway is that the “winner” depends on which layer you evaluate. Claude Code may win on speed and immediate product usability, while Codex may win on architecture, testing and reliability. I’d score them separately on time to first usable version, regression coverage, failure handling, maintainability after several changes, and total cost. Giving both tools the same prompt is a useful baseline, but it may not represent the workflow in which each agent performs best.
Workless AI event in Montenegro!
This event has been amazing. There's not much that energizes me more than being in a room of a bunch of people who are all working hard to grow! I also got to meet a TON of you guys which makes me so happy. I didn't get a picture with everyone, but here are a few. You can even see @Duy Nguyen repping AIS. What a guy!! Montenegro is a beautiful country. Highly recommend adding it to your travel bucket list. Hope you guys are getting pumped for our first AIS in person event!! - Nate
Workless AI event in Montenegro!
5 likes • Aug 3
@Muskan Ahlawat of your AI-OS+++ functionalities? I only want to understand what type of task or pipeline you use
5 likes • Aug 3
@Muskan Ahlawat I am looking for practical usecase. Because of that I asked.
Claude again problems 3 times today . ERROR , 529 . 500
Who else has trouble with the Claude code . Simply start to hate this company today I had 3 incidents . Who else
2 likes • Jul 29
I am experimenting with openclaw and have built over 20 agents
0 likes • Jul 31
@Frank van Bokhorst what do you mean exactly? A kind of middleware?
1-4 of 4
Emre Er
4
78 points to level up
@emre-er-8109
Manufacturing Engineer | Industrial AI · Automation · Data & Software | Automotive & Smart Manufacturing

Active 23h ago
Joined Jul 14, 2026
Stuttgart
Powered by