In Week 2 assignment i rebuild AI Automation for Digital Marketing B2B, included my website https://digitalimran.xyz

I spent this Sunday building something interesting outside of the official assignment; a Mini RAG system for LinkedIn content using n8n + Google Sheets + Gemini. The goal: 👉 Scrape high-performing posts from top AI creators 👉 Extract structural patterns automatically 👉 Generate fresh LinkedIn posts in my voice, based on proven formats Here’s how it works: 🧩 Workflow A : Pattern Builder 1. Fetches raw posts from a Google Sheet (just post URL + content pasted manually 2. Loops through each post 3. Sends the content to an LLM and returns structured data: ✔️Hook type ✔️Hook example ✔️Post type ✔️Tone style ✔️CTA style ✔️Writing tricks ✔️Key ideas 4. Saves everything into a Pattern Library Sheet This turns long unstructured posts into a database of writing patterns. 🧩 Workflow B : Post Generator 1. I enter simple inputs: ✔️Niche ✔️Target audience ✔️Post type ✔️Topic hint 2. The system: Reads multiple patterns from the library Summarizes them into one master pattern prompt Generates: ✔️ LinkedIn post ✔️ First comment ✔️ One-line summary Then emails the output to me automatically. 🧪 Status & Screenshots ✔️ The system works end-to-end ✔️ I received my own AI-generated LinkedIn post + comment by email ⚠️ Hit a Gemini API quota after processing several posts (classic 🤣) No paid tools. No external scraper APIs. Just n8n, Google Sheets, and manual LinkedIn/X copy/paste. 🧠 What I learned today: - Studying real posts beats “write a LinkedIn post like a human” prompts. - Data beats creativity. I can replicate viral positioning based on structure and data, not luck. - Workflow chaining in n8n finally clicked today. 📅 Next steps: - Add batching + retry logic to avoid API limits - Auto-scrape LinkedIn comments for CTAs and hook variants - Export pattern library to Airtable or Notion

🔥 Overview For Week-2, I rebuilt the AI lead qualification workflow for personal finance education & coaching niche. This automation: - Takes form submissions from leads - Scores lead quality based on their financial readiness - Assigns a qualification tier - Automatically sends different emails depending on score - Logs the complete lead + score + next steps into Google Sheets All built in n8n without any coding. 🧠 AI Agent – System Prompt 1. ROLE You are Pankaj’s inbound lead qualification agent for his personal finance education & coaching business. 2. TASK You will receive one JSON object with these keys: - lead_name - lead_email - monthly_income - monthly_expenditure - financial_goal - help_required - current_investments - lead_source Your job is to: - Score the lead from 0–100 (lead_score). - Decide a tier: - A_1to1 (score ≥ 80) - B_Webinar (score 50–79) - C_NoEmail (score < 50) - Say if they are qualified (true/false). - Write a short summary, reason, and recommended_next_step. - For qualified leads (score ≥ 50) write email_subject and email_body. - For non-qualified leads (score < 50), email_subject and email_body must be empty strings "". 3. CONTEXT Pankaj helps salaried individuals in India build long-term wealth using mutual funds and simple planning. Good leads usually: - Have regular income. - Have positive surplus: monthly_income > monthly_expenditure. - Have clear or semi-clear goals (retire early, pay debts, child education, wealth building). - Are asking for guidance, planning, or education. Weaker leads: - Very low or negative surplus. - Only want “quick money” tips. - Say they cannot pay for anything soon. - Spam or random requests. 4. SCORING GUIDE First, estimate monthly surplus = income - expenditure (roughly from the text numbers). Use this as a guide: - Surplus > 30,000 → strong readiness (+40 points). - Surplus 10,000–30,000 → medium readiness (+25 points). - Surplus < 10,000 → low readiness (+10 points).

👋 Hey everyone, I am Pankaj Vashist! I am based in Gurugram, India and currently work full-time in the banking industry (15+ years of experience). I have recently started my AI journey because I want to leverage AI to build real systems and solve practical problems. 🎯 Why I joined Uniteck AI ✨ I have known Eila through DD’s Digital Mentor program and really appreciate her clarity and teaching style ✨ I want clarity of thinking, not tool-hopping ✨ I learn best in a structured environment ✨ I’m here to learn how to build AI projects that make a real business impact 🚀 My goals over the next 90 days ⚡ Complete the full 10-week Agentic AI program and apply each concept with a real build ⚡ Strengthen fundamentals in prompt engineering, problem decomposition, and multi-agent orchestration ⚡ Build 5–7 functional AI workflows end-to-end using real world use cases ⚡ Stay consistent, participate actively, and connect with other builders in the community ⚡ Connect with like-minded people and learn from the community Excited to be here and looking forward to learning, sharing ideas, and growing together! 🙌