I watched Nate's Lovable and n8n and is amazing. I want to try it but I have a question. I have a multi-agent setup, the n8n data and fields I want to sync (Calendar events and Gmail messages) with my Lovable organizer project are in one of the children (sub-workflows). Do I get the Webhook from the Parent Agent or from each of the sub-workflows (emailAgent and calendarAgent)? I ask this because the Parent Agent has a very strong infuence since all queries go through the Parent but for the sake of simplicity I was thinking is best to use the sub-workflow webhooks because all I need is to sync email and calendar data in my Lovable dashboard. I appreciate your help. Thank you

Want to dive deeper into this build and discuss how to enhance it? Join AIS+ In this tutorial, I’ll show you how to integrate OpenAI’s new reasoning model, O3 Mini, into n8n to build AI agents that support tool calling. A reasoning model that can call tools, like OpenAI’s O3 Mini, is a game-changer for AI agents because it allows them to take action beyond just generating text. Unlike models like DeepSeek R1, which are purely reasoning-based and lack built-in tool-calling capabilities, O3 Mini can interact with external APIs, databases, and applications in real time.

Hi there, I'm new here and already looking for help ;) i'm trying to automate my expenses and coming up against some issues getting inconsistent results. I need to take a photo of a receipt and pull value etc off it. I'm using chatgbt. The problem being its hallucinating half the data. How would the group go about it?

Want to dive deeper into this build and discuss how to enhance it? Join AIS+ In AI Personal Assistant 2.0, I set a goal of 1,000 likes to make a step by step. You guys crushed that. As promised, here is the tutorial! I even added a bonus element of talking to the agent and having it talk back. Hope you guys enjoy! Let me know your thoughts on this one! The HTTP Request Body JSON: { "text": "{{ JSON.stringify($json.message.content).replace(/(^\"|\"$)/g, '') }}" }

In this video, I showcase how I built a simple AI-powered Invoice Agent using n8n with no code! I walk through creating a workflow that takes an invoice image sent via Telegram, uses an OCR (Optical Character Recognition) API to extract text, populates the information into a database, and uploads the original image to Google Drive. The agent then provides a quick summary of the invoice, along with the file name and a database link.