Hello everyone, I hope you’re all doing well. I’d like to ask one thing: I’m using the Blotato node in an automation that I built to upload videos to YouTube. The automation is saving me a decent amount of time, but IT’S NOT fully automated. That bothers me a bit 😅 So this is my situation: the video gets uploaded to YouTube with title, description, and hashtags ready (good, just like I want it). However, I still need to go into the video (Within YouTube Studio) and tick / select the following options: “Altered content” (I need to select the option “No”) “Featured places” and “Automatic concepts” (I need to untick both options) BUT THE MOST IMPORTANT THING (and annoying), I still need to select the language used for the video, title, and description because the Blotato node doesn’t give me that option. I have uploaded all the screenshots above. Do you have any idea how I can upload these videos with all these features already checked / selected / unticked? Will I need to use an HTTP request node instead of the Blotato node? Have you done this before? This is my own automation, so technically speaking, I can kind of spend a bit of time manually doing these small tweaks, but that defeats the purpose. I keep thinking, "ok, what if it was a client and the client wanted this process FULLY automated?" If anyone knows how to do this and can share their knowledge, that would be greatly appreciated. Thanks in advance.

Hello n8n veterans and power users, I’d love your opinion. Which option do you think is best for running n8n? Do you prefer n8n Cloud (€24 / ~US$28 per month), or do you prefer to self-host with a provider like Hostinger or TMD Hosting? The cost difference is pretty significant. With my self-hosting plan (I use TMD Hosting) I pay US$120 per year (about US$10 per month). Apparently, when you self-host you also get unlimited workflow executions. I’ve been learning n8n for the past month using the Cloud version, and I’m now thinking of cutting costs and switching to self-hosting. Do you think the savings are worth the switch? Which option would you recommend and why? For context, I’m currently using n8n for my own workflows, but I intend to start building automations for clients soon. When you create automations for clients, do you ask them to create an n8n Cloud account, or do you recommend they self-host? Thanks in advance, I’m keen to hear your experiences!

Hey everyone, I could really use some help with this issue I’ve been stuck on for the past few hours. I’m building a simple agent that: 1. Collects information from the user via chat 2. Passes that information to a sub-agent, which updates a CRM (HubSpot in this case) I decided to use a sub-agent approach because I plan to add more tools later, and I didn’t want the main prompt to become bloated. The idea was to keep things modular and dynamic. The problem:Whenever I provide the last required detail, the sub-agent successfully calls the HubSpot tool and gets an “ok” response. At that point, I’d expect the agent to stop and return the confirmation message back to me in the chat. Instead, it enters an infinite loop: - It keeps calling the same tool over and over, even though the first attempt already succeeded. - Eventually, it crashes with “agent stopped due to max iterations”. - Looking at the logs, I can see that the tool succeeds in the first iteration, and the main agent even produces a valid response that could have been returned to me—but instead, it just restarts the process and re-executes the tool. Question: Has anyone else run into this looping behavior with sub-agents and tool calls? Is there a known fix or a pattern I should be following to make sure the agent stops after a successful call? I’ve attached a snippet of the logs below for context. You can see the sub-agent succeeds on the first try, but the loop continues anyway. Any insights would be hugely appreciated,this is driving me nuts.

Competitor charges client $4k/month. I rebuilt their entire system in n8n for $47/month. Client switched. The client showed me EVERYTHING. Here's exactly how to compete with overpriced "enterprise" solutions: THE DISCOVERY CALL Client: "We pay $4k/month for document automation" Me: "What does it do exactly?" Client: "Processes invoices" Me: "...that's it?" Client: "Well, it has a dashboard" 🚩 Red flag: $4k for invoice processing COMPETITIVE INTELLIGENCE (2 Hours) I signed up for their competitor's free trial. Company name: "Enterprise Document Solutions" What I discovered: - AWS everything (unnecessary) - Custom React dashboard (barely used) - "AI-powered" (it was regex patterns) - 24/7 support (client never used) - Processing: 3,000 invoices/month Their actual logic: 12 steps of basic extraction MY REBUILD (Saturday Afternoon) Built the EXACT same functionality: **The n8n Workflow:** 1. Gmail trigger → monitors inbox 2. PDF parser extract → handles all formats 3. Validation → simple IF conditions 4. Google Sheets → client preferred this 5. Slack alerts → for exceptions 6. Daily summary → automated email **Time to build:** 3 hours **Nodes used:** 6 **Complexity:** My 12-year-old could maintain it THE COST COMPARISON **Their "Enterprise" Solution:** - Software: $4,000/month - Hidden AWS costs: $200/month - Setup fee: $10,000 - Training: $2,000 - Annual cost: $52,400 **My Simple Solution:** - n8n hosting: $5/month (DigitalOcean) - PDF Vector API: $16/month - Total: $47/month - Setup fee: $2,500 - Training: 30-minute Zoom - Annual cost: $564 THE PERFORMANCE COMPARISON **Processing Speed:** - Theirs: 45 seconds per invoice - Mine: 3 seconds **Accuracy:** - Theirs: 94% - Mine: 99.2% **Maintenance:** - Theirs: Weekly "updates" (breaking things) - Mine: Hasn't been touched in 3 months THE SWITCH Showed client the demo. "This does everything?" "Everything and more." "For $47/month?" "Plus my management fee." "Which is?"

Hello everybody. Can someone let me know what I’m doing wrong? My scenario is: I have 100 videos that have been uploaded to Google Drive and their files names have been written in a GoogleSheet. The idea of the workflow is, first, it will look for the filename (Get_rows node) then if the status is “todo” and the video URL is not empty (check one node) it will extract the video URL (extract URL), after that if fileID is not empty (check Two node) it will go to batches and 3 videos will be processed every time. 3 videos will be downloaded, transcribed and my LLM Basic Chain will create a title, description, hashtags etc based on the transcription. My idea is to fill the spreadsheet columns (“title”, “description”, “hashtags” and “x_description”) with the information produced by the LLM Basic Chain node.However, I run into an issue. For example, every 3 videos that are processed (batches) rows 2, 3 and 4 gets updated in the spreadsheet. So basically if I run the workflow twice, the data gets overwritten because rather than adding the new data (second batch of 3 videos) to row number 5, 6 and 7 (for example) the new batch overwrites rows 2, 3 and 4, so I end up with the data from videos 04 (row 5), 05 (row 6) and 06(row 07) in the row 2, 3 and 4. This is hard to explain, but do you understand what I mean? I’ve tried to map this out using the filename (which is unique) and row number but I keep getting this behaviour. What I want is the workflow to fill the rows based on the filename, not overwrite the information. Do you know what I’m doing wrong and how I should fix this? Thanks in advance for your input!