🤖 LinkedIn Automated Content System — built and tested end-to-end Wanted to share a workflow I put together (n8n) for automating my LinkedIn content, niched down specifically to hospitality (hotels) and hospital/healthcare automation topics. How it works: 1. I send a topic to my Telegram bot (or trigger it manually for instant posts) 2. It filters out anything that's not hospitality/hospital-related — keeps the content strictly on-niche 3. Pulls real research/facts on the topic instead of hallucinating stats 4. Writes the post in my voice using Gemini 5. Generates a matching image 6. Sends me the preview on Telegram with two real buttons: ✅ Approve & Publish or ✏️ Request Changes — no typing needed 7. If I approve, it publishes straight to LinkedIn and confirms back on Telegram 8. If I ask for changes, it loops back for a revision A few things I learned building this: - Telegram's sendAndWait node with button-based approval is way cleaner than free-text replies - Photo captions on Telegram have a 1024-char limit — learned that the hard way - Free image generation (Pollinations.ai) works great for this, no OpenAI billing needed - Keeping the topic filter simple (a keyword regex) does 90% of the job for keeping content on-niche Happy to answer questions if anyone's building something similar!

This is Day 1 of my 100 Days of AI Automation series, where I'm challenging myself to build 100 AI automations. And for Day 1, I built an AI-powered Email Summarizer. Here's how it works: 1. 📩 A new email arrives through Gmail 2. 🔍 AI classifies the email into: - Needs Attention - Waste of Time - Not Sure What This Is 3. ⚡ Important emails move forward 4. 🧠 AI summarizes the email and provides a quick TL;DR 5. 📲 The summary is then sent directly to Telegram The idea is simple: instead of manually going through every email, AI helps filter out unnecessary emails and gives you a quick understanding of the ones that matter. This is just Day 1 of 100. Still 99 automations to build. 🚀

v2 of my AI Ticket Triage Assistant is done — fully verified, no loose ends. Quick context: v1 handled single-issue tickets fine, but couldn't handle tickets describing more than one problem at once (e.g. "VPN down AND can't access SAP"). It would just pick one and route on that alone. What I built for v2: - Extended the extraction step to detect multi-issue tickets, not just classify single-issue ones - Added a new top-priority routing rule — any multi-issue ticket goes straight to Service Desk for human triage, overriding the normal category/priority logic - Ran regression tests against my original single-issue tickets (Okta SSO, Office WiFi, sticky-keyboard) to confirm nothing broke - Manually checked every wire on the canvas — all 5 Switch outputs correctly connected, with Service Desk properly receiving both the multi-issue path and the fallback path The part I actually want feedback on: two backlog items surfaced naturally through this process, and I'm deliberately not building them today 1. Error handling for malformed Gemini output (what happens if extraction returns something unexpected) 2. A design smell — 4 near-duplicate Log nodes that should really collapse into a single Merge-then-Sheets-node structure Leaving v3 alone for now and writing these down instead of chasing them immediately. Anyone here dealt with #1 in production — how do you handle malformed structured output from an LLM node without the whole workflow breaking downstream? Difference from the LinkedIn version: no hook engineering, leads straight with the technical summary, and the closing question is a real technical ask (error handling for malformed LLM output) rather than a reflective prompt — matches how the community actually engages, based on Raj and Chetan's past comments.

Just finished my first real n8n build — an AI Ticket Triage Assistant for ITSM, using n8n + Gemini. Quick context: I work as an ITSM Analyst day-to-day, so I built something close to my actual domain — support tickets come in as messy free text, and normally a human has to read, judge urgency, and route each one manually. v1 pipeline (kept deliberately simple, no agents/chatbots): 1. Raw ticket text goes in 2. Gemini extracts structured data — category, priority, impacted service, suggested team, summary 3. Deterministic rules (not AI) make the final routing call — e.g. High priority always goes to Major Incident Team first 4. Every decision logs to Google Sheets, AI's suggestion vs. the system's final call, side by side Design choice I stand behind: AI suggests, business rules decide, everything's auditable. Didn't want a black box, especially thinking about how this would actually need to work in a real ITSM environment. Bugs I hit (sharing since debugging seems to be most of the actual skill): - Deprecated Gemini model throwing silent 404s - Google Sheets OAuth needed both Sheets AND Drive APIs enabled - A wiring mistake silently misrouted tickets — only caught because I tested varied fake data instead of trusting the first clean run - Gemini initially over-weighted urgency language ("asap") over actual business impact — fixed by separating requester tone from objective impact in the prompt Tested against 10 varied fake tickets, all routed correctly. Planning v2 next: multi-issue ticket detection, since real tickets are rarely this clean. Would love feedback from anyone who's built something similar — especially on the human-in-the-loop pattern (AI suggests / rules decide / log everything). Is that overkill for v1, or the right instinct to keep from the start?

Hi everyone I'm based in Melbourne. Background is SMB and mid-market B2B SaaS Sales. Short term goal is 1st client within ~30 days (sales/GTM automation). Longer term (1–5 years) is to design, implement, and own GTM architecture and strategy at an enterprise level, ultimately in a C-suite or directorial capacity. Why? I want deep, hands-on confidence in business transformation (AI preparedness -> integration with legacy tech stacks). I’m especially keen to connect with current or former corporate managers/executives who are also early in this journey — particularly anyone Melbourne or Australia-based. If you’re coming from a serious operating background and asking, “How do I apply this responsibly and commercially?” I suspect we’ll have plenty to compare notes on. Very open to coffee chats - If you’re Melbourne-based and early in this transition, feel free to DM here or on Linkedin — always keen to trade notes in person. - Sherwyn