When using self-hosted NAND, the Gmail node requires a client ID that I can only get by linking my bank account to Google Cloud. Do I need to ask clients for their bank details, or is there another way?
You definitely don't need your client's bank account details; they only need a Google Cloud account. On a kickoff call, walk them through setting up Google Cloud, screen‑share if helpful, and coach them through the process without asking for card details. After they’re set up, take the Google Cloud client ID and secret and add them to your NAN. That’s the straightforward way to solve the immediate problem. However, honestly you shouldn’t have this problem at all—self‑hosting turns a simple automation logic task into a DevOps and coding burden (environment variables, webhooks, reverse proxies, etc.) that adds no real value for the client. A better approach is to use the cloud‑hosted version of OOTH (or similar), which is simple, always supported, avoids downtime, and lets NAN handle errors for you. The cost (e.g., $25–$60/month) is tiny compared to the value you deliver; if you’re not getting at least a 20× ROI on that spend, you probably shouldn’t be building the system for the client in the first place.
He recommends always hosting the systems on the client’s NAN (their account) so handoff is easy—you just give them the account and walk away. Hosting on your own account creates extra work like handoff documents and training, and while you lose some leverage, he prefers leading with value and avoids the reputational risk of seeming controlling.
I recommend that if you're self‑hosting AnyTrack, you actually shouldn't self‑host because the authentication steps become a pain. Most of the Google Cloud Console work you’re doing manually can be avoided by using the cloud‑hosted version, which provides a one‑click OAuth connection. You simply click “Connect with Google” and it signs in for you. If you do need to handle the Cloud Console steps, schedule a kickoff call with the client after you receive payment. During the call walk them through the process, have them share their credentials, and complete any two‑factor authentication live. Doing it live ensures that even if the OAuth token or 2FA expires, the integration remains in AnyTrack. By the end of the call you should have everything set up so you can start the client project without having to ask for additional access later, which keeps the process professional.
Yes, the best option is to pay the default fee for a carefree experience with all the hassles. I'd love to see a video on this, as I was almost tempted to go self-hosting and learn the platform. I've tons of experience breakinging down barriers and obstacles of self-hosting and common apps affected by it, and how much more effort and time is needed to manage and maintain. Suffice to say, the reason I typically recommend cloud hosting everything is that you don't have to deal with deployment, DevOps, or additional environment variables and similar self-hosting concerns. As an automation specialist, believe it or not, your main point of value is not in your technical knowledge; it's in knowing just enough of the technicals to apply them to real business processes. Then you spend the rest of your time becoming a business person, a business expert. That's where the leverage lies with the alpha people who get really into self-hosting—they often lose the cart for the horse, spending so much time figuring out every little technical detail, spinning up Docker containers, getting environment variables right, and doing EngineX pass-through for webhook URLs. It's incredible how much time that takes. My recommendation is to focus on the things you actually get paid for—delivering value to your clients—not on designing the most optimal, technically and academically perfect solution.
I don’t actually sell these AI agents myself; I don’t find them super valuable right now. I don’t think they’re more valuable than a traditional linear left‑to‑right automation, and the agency aspect doesn’t make my clients’ lives better or solve a unique problem I couldn’t just build easier with a linear flow. In general, what you should do is first try to sell the thing before you’ve built it. Go out, hear what people have to say, learn their pain points and what they want, and assemble enough validation or proof that the service is in demand. Only then should you actually go about building it. AI agents are a bit special because they’re very easy to set up—you literally just drag and drop an agent node and say a couple of magic words and it works about 80 % of the time. If you’ve already built it, I get it, but for future reference, sell first. When you sell it, tell them your goal is to make the process as easy as humanly possible, that you don’t want to lock them into anything, and you want to give them maximum freedom and autonomy. Walk them through setting up NADN (the no‑code drag‑and‑drop platform I used) on their account. Have them sign up with their credentials, then use those credentials to access the account—this makes handoff easy if they later choose not to work with you. It also makes managing everything simple and gives them total control, which I think is fundamentally important. Have them sign up for the cloud plan, don’t self‑host, and run the NNA agent on that cloud plan for them. On the kickoff call, make sure you get all credentials, handle any two‑factor authentication, and take care of Google console access if needed (with make.com you just need Google account access). When you do the implementation, hold their hands: make them open the browser, open NADN, sign up, and then get the username and password. Ensure any accounts you use for this purpose aren’t created with OOTH, otherwise you’ll have Google‑based 2FA, which is a pain. Confirm they can sign in, then you’re building it all on their account. Don’t sweat the building before you sell—sell first, then build after.