In this video, I compare OpenAI’s new AgentKit to n8n to see how they stack up against each other. We’ll go over what each platform is, how they work, and what makes them unique. I’ll walk you through how to access and set up AgentKit, explore its features, and then put both tools head-to-head across different categories. I also score each one so you can clearly see their strengths and weaknesses. Most importantly, I’ll help you figure out when you should use one over the other, because the truth is, they’re built for different purposes and appeal to different types of builders. Whether you’re just getting started or already deep into automation, this video is a full, easy-to-follow guide to help you choose the right tool for your next project.

The n8n team has officially announced: A completely new UI and UX is on the way! 🧠✨And this brings with it some exciting changes: 🆕 What can we expect in concrete terms? ✅ The new Flow Builder UI Editor is getting a fresh, modern design - with a better overview and clearer structure. This makes complex automations much easier to build and understand. ✅ Complete UX redesign is not just about looks - the entire user experience is being overhauled: more intuitive, faster, smarter. Whether you're just starting out or already a power user. ✅ Improved navigation & usabilityThe entire operation is more logical and fluid - from flow management to editing individual nodes. ✅ More speed & efficiencyThe new version is also designed to improve technical performance - a real boost, especially for large workflows and many active nodes. ⚡

Hi guys I'm either struggling with something dead-simple or near-impossible; I can't seem to figure out how to post a file or an image to model (Gemini or OpenAi or whatever) and interrogate it against a vector store. It's almost exactly the functionality found in ChatGPT's Projects area; you can add a bunch of files which gets turned into the project's vector store and then you can interrogate this vector store via chat alongside file uploads. In a perfect world there would be an agent that has access to a vector store and then pulls a file from Airtable and queries it. I'm not sure if this is possible though; if there other flows that make it happen I'm all ears..

Hi guys I have a general 'how to approach' things question re how best to structure vectorstores (Pinecone in this case): I have a Pinecone Index (knowledge_base) with a namespace in it (called 'docs'). It's constituted of 20+ PDFs that were ingested via an n8n pipeline. All good on that regard. The next step would be to query another handful of PDFs 'against' this index. I can run the same 'ingesting' flow for this query and now have 2 options: 1. Create a new vectorstore (query_1 etc) with these new info 2. Update the same vectorstore with namespace (query_1 etc) I can see on n8n that I can dynamically set either the ID of the index or the namespace of the index so on both counts it should be arbitrary to setup a tool for the query itself; as the tool for the knowledge_base is static and doesn't change. Which route would you suggest? Multiple indexes or one index with multiple namespaces?

Hello. Why can't I add the previous nodes info to create an output in the merge node?