Hello everyone! Last night, I was able to do all this in one go and to my shock, at the end of it my build was almost done! 1) Created a telegram bot using BotFather. 2) Added a telegram trigger with the credentials set up and testing connection. 3) Connected Google Sheets for expense tracking 4) Connected Gmail for alerts incase the threshold expense gets crossed✅️ 5) Tested reading and creation of expense rows and mail trigger well✅️ 6) Top of it all, the Gemini 3.5 flash model I attached was also able to read through image input and then provide right analysis to me✨️ Compared to Meta webhook and testing, telegram was quite easy. I wax able to quickly navigate the bot, find the chat id and then chat with it using my current tunnel approach Attaching relevant pieces of output and build for your reference. Until next build, LFG!! 🚀🚀

Following on my last post where I set up the n8n assistant, now I have been able to connect it to my docker engine through Docker Desktop application and a bunch of other configurations and secrets for connecting the sandbox and n8n seamlessly. I was able to use OpenRouter's free models in the chat with assistant option when you are building a workflow on n8n canvas. It seems so real that now we can leverage the non-deterministic nature of these LLM models, to itself make an agent that is well deterministic. My next build is scoped around the use of Telegram to analyze the receipt of any expenditure made by a business owner and then tracking the entire expenses stored on a database. Till then, let's keep on building ya'll 🔥🚀🚀

Just wanted to pause and take a moment to share my growth in the AAA community so far. I am standing at 8th on this week's leaderboard! Happy to finally say that I have been an active member here for quite some time now. Glad to be among such people who really really help me think beyond the box, try something new every time and provide such genuine space where I can communicate any kind of ideas or issues I am stuck with! To any new person reading this, just stay active, post when you know some context of what you need and the steps that have you taken yourself to resolve it (even a bit), and then describe your issue and post it in appropriate category. Onwards and upwards! 🚀🚀🎉

Got past the first step of seting up env for using n8n assistant but to be still abel to use the n8n ai builder locally, iI need to set these thigns up!! What kind of sandbox is to be used here? Pls help and also tell any cheaper alternatives if you guys know 🙏

As promised in my last post, I am back with a new build and this time it's straight from LinkedIn. You’ve probably seen the “Comment GUIDE and I’ll send it over” posts everywhere. But have you ever wondered what happens behind the scenes to track those comments? 👀 This week, I tried building that workflow myself with n8n. Here’s what it does: ✅ Takes a LinkedIn post URL and a keyword ✅ Pulls every comment from the post ✅ Filters the people who actually asked for the lead magnet ✅ Logs them in a sheet and emails me a quick summary The workflow connects a few different tools: 1. 𝐀𝐩𝐢𝐟𝐲 🕷️ for fetching the post comments through an HTTP request 2. A 𝐂𝐨𝐝𝐞 node 🧩 to clean up the raw data into name, profile, comment and timestamp 3. 𝐆𝐨𝐨𝐠𝐥𝐞 𝐒𝐡𝐞𝐞𝐭𝐬 + 𝐆𝐦𝐚𝐢𝐥 📊 to store the leads and send the summary What I learned the most wasn’t in the workflow itself, it was in the roadblocks 😅 LinkedIn’s official API keeps comment and engagement data locked behind approvals for most apps. I fought OAuth scope errors before realizing I should change the approach, not the error message. Still a prototype, but going from “this isn’t possible” to a working flow in a weekend is what keeps me hooked on automation. What’s one manual follow-up task in your work that you’d love to automate? #AI #Automation #n8n #LeadGeneration #BuildInPublic #WorkflowAutomation #SoftwareEngineering #Tech