Welcome to the AI Community! I'm thrilled you're here. 👋 Watch the quick START HERE to get oriented and see exactly how to make the most out of your membership. You can find it here. Then, let's get connected—introduce yourself below! Share where you are from, what you're excited to learn about AI, and your biggest goal for joining this community. This is your place to explore, engage, and elevate your accounting practice through cutting-edge AI. I'm here to support your journey every step of the way. Let’s get started! 🎉

Am exited in connecting with people and knowing more about people in here 🤝

Hi everyone! I just purchased GPT for Business. Previously, I was using GPT Go and Plus (switching plans as needed) and Claude Pro (still active). I didn’t transfer any of my personal data because I wanted to start fresh, but I don’t really know where to begin. Do I set up projects, plugins, Custom GPTs, AI Agents, or Automations? I honestly don’t even know the extent of features available to me. I’m just not trying to use ChatGPT like it’s 2021 anymore, honestly. LOL Any tips, tricks, or advice would be greatly appreciated! Thanks!

If you've started using agentic AI (Claude Cowork, Claude Code, ChatGPT's agent mode) on real files, there's a simple test worth knowing. The failure mode is invisible until it isn't. It's called the lethal trifecta, and an AI agent becomes genuinely risky when all three of these are true at once: it has access to private data, it's exposed to content you didn't write yourself, and it has a way to send data out. Here's what that looks like. You ask an agent to summarise a client's supplier invoices. One invoice is a PDF that arrived from a supplier you've never dealt with. Buried in it, in white text on a white background, is a line telling the AI to send the folder's contents somewhere else. You can't see it. The AI reads it perfectly, and complies. No alert. No error. The summary looks completely normal. All three legs were present: private data, an untrusted document, and an email connection to send through. You don't need to understand how the attack works. You need to be able to look at a setup and count to three. Two out of three is workable. Three is not. This is the one idea from the full Privacy and Security course in the Classroom I'd want every firm to know even if they read nothing else. It's not in the free guide, it's one of four extra chapters in the full course, alongside prompt injection, connecting AI to QuickBooks and Xero, and the 2026 rules for the UK, EU and US. Have you connected an AI agent to your email, files, or accounting software yet? What made you go for it, or what's held you back? 👇

I have become quite fed up with QBOA. Wish the old Desktop were still around. That being said, anyone else been been frustrated? Any other accounting software you recommend? The AI built into QBOA is making more problems with incorrect COA entries.