Hey everyone! We’re looking for experienced automation builders familiar with tools like n8n, Make, or Zapier to join our early beta testing group for AFK Crypto — the first platform that enables on-chain crypto automation directly from your favorite no-code tools. This is a free gig — we’re not offering payment yet, but you’ll get exclusive beta access and help shape how automation connects to the blockchain. Your feedback will directly influence the product and future integrations. If you’re passionate about AI agents, automation, and crypto, this is your chance to be part of something cutting-edge from the start. Only 50 slots are available, and they're filling up fast! 👉 DM me if you’re interested in joining! :)

After 3 Days of pushing, I'm finally able to complete my very first RAG. My use case is really simple: A Personal Blog Assistant that will turn my raw/dumped ideas into a ready for review and editing blog content, that is also relevant to my ebook, so I can also promote it as I post this article. My learnings this time: 1. Knowing how to transpose or manipulate the upstream data so its useful and accepted downstream is important. When I was designing my retrieval workflow, I thought it will just be simple,I just have to fetch whatever I have from my notion page, and then pick up one attribute from there to use that as a search string for my ebook lookup agent. But it wasn't that simple, here I again hit many walls (😅), so I had to learn how the outputs in JSON work and research what available nodes for data could be used. In this case, having a personal GPT speed up my hunt. It's a super plus because its able to explain my questions and help me understand how a specific node works and what it is for. 2. Chunking the upstream data helps simplify the downstream fetch. This was specifically significant for my Search Agent, because the Simple Memory that I hooked is only able to process 1 execute output and key at a time. The Text Classifier, Set Node and the Custom JS script (of course with the help of my personal GPT) satisfied the Simple Memory's requirement. 3. From Friday to today I've sent around 200+ tokens (this involves 2 OpenAI calls- 1 for the search agent, and 1 for the blog generator), with both of these running, I've spent a total of $1.69. That's pretty decent, that's like equivalent to 5~ articles (including the ebook search). Overall I'm so happy, because I'm able to complete this test project, and I feel like I'm ready to take on more experiments and soon solve real business problems, I actually have one already related to my profession a QA Navigator that gathers story/requirements context, past bugs, past test cases and then from there suggest possible issues,gaps and test designs....I hope I can do it hehe...

Building my first RAG I'm finally able to complete the very first component of my first RAG. So far, I'm beginning to understand that the success of the workflow's execution is in the correct configurations of the moving parts. My challenges around the configuration is on making the Google Drive - Download File node work. I hit many walls trying to make it work with OAuth2, but for some reason, my access gets blocked. So because I want to succeed by this time, I took a pivot. I tried connecting via Service Account and that simplified it. With this though, manually adding the service account (Google Cloud) to the file as an Editor is necessary, so the expected file that you desire to retrieve is returned in the n8n dialog. With Pinecone, I hit another wall, my execution returned a dimension mismatch error between the index and the vector, so I had to recreate my index. Today was indeed a mental workout 😅 Up next is the second component of this RAG - which is the agent, will share more about that next time. I'm planning to connect this with a personal editor/content refiner agent for my personal blogs, that will return my dumped ideas into ready content that I can just review and then post 🤩 Let me know in the comments what are your challenges, interested to learn from you as well 😍 #happyBuilding

A Personal Expense Manager. I'm so happy to share here, that by just watching Nate's masterclass video (the first 30 minutes of it), I'm now able to create a workflow that summarizes personal expense, creates a report (appends that in the same expense tracker) and sends a summary with recommendations for spending control here are my outputs:

Let's get to know each other! Comment below sharing where you are in the world, a career goal you have, and something you like to do for fun. 😊