Downloading resumes. Updating the ATS. Sending acknowledgment emails. So we automated the process. Every new application is logged, organized, and the candidate receives an instant response. The recruiters now spend more time talking to people instead of managing spreadsheets. What's one HR process you'd automate first?

Most CRM records are incomplete. A contact enters with a name, email, and company name and stays that way because nobody has time to manually research every lead. I built an enrichment workflow which when triggered on new contact creation can pull LinkedIn data, company size, industry, revenue range, technology stack, and recent news about the company, then write all of it back to the CRM record automatically. An LLM pass on top of that data generates a personalised outreach angle based on the prospect's apparent priorities and the problems your service solves. The sales rep opens the CRM and finds a fully populated record with a suggested talking point already written. The research took zero of their time. See visual representation of the platform below.

🚀 Just shipped: BFS Suite (Big For Small) — a multi-agent AI support system built entirely with n8n + RAG Here's what I built: 3 specialized AI agents under one roof: → Legal agent — contracts & compliance → HR agent — policies & onboarding → Support agent — FAQs & troubleshooting Every query goes through an AI Router (GPT-4o-mini) that classifies the topic and routes to the right agent in real time. ⚙️ Under the hood: • RAG with pgvector similarity search (Supabase) • Dual access: public web widget vs internal dashboard • Knowledge gap detection — unanswered questions logged automatically • Escalation via Telegram — 3 triggers: low similarity score, explicit user request, or ambiguous routing (Legal/HR overlap) • Human-in-the-loop — when the router's confidence drops below 0.7, the query goes to a human instead of guessing • Full analytics dashboard with live charts • Document upload straight from the dashboard 🛠 Stack: n8n · GPT-4o-mini · Supabase (pgvector) · Netlify · Telegram Bot API 📊 5 workflows: Ingestion → Query → Logging → Upload → Escalation Everything is production-ready — real RAG, real logging, real escalation. Not a toy project. 🔗 GitHub: github.com/Evgeniy1970-ai/bfs-suite 🌐 Live dashboard: charming-sable-0dd4f8.netlify.app Happy to answer any questions about the build — drop them below 👇

Wanted to give a shoutout to @Alexander Cebulla. Closed his first large automation customer (5 figs). Alexander you will not forget that feeling. It will fade a bit when you close more in the future, but you won't forget it. I still remember my first freelance client from 2021, my first enterprise customer, and my first 100k customer. Happy for you. Use the momentum to deliver the highest quality results. Remember it is always easier to keep current clients happy than it is to land more clients.

Built my first working n8n automation lab (commit 1). Goal was simple: a local setup where I can build webhook-based automations, but still expose them to external services when needed. Stack is pretty minimal: - n8n in Docker - Postgres for persistence - Cloudflare Tunnel for public webhook URLs - small shell scripts to start/stop/test everything What matters: - I can tear it down and rebuild it cleanly - workflows persist across restarts - webhooks work externally via a temporary public URL - local UI + external access both work at the same time Next step is building reusable automation patterns (webhook → transform → API → response). This is the base layer for everything I’ll build on top.