Azhar Farooq
AI automation specialist building n8n workflows that scale.
New to Contra
Azhar is building their profile!
This n8n workflow automates content creation and publishing end-to-end. It pulls a row of content ideas or prompts from a connected Google Sheet ("Get row(s) in sheet"), then hands that data to an AI Agent (powered by an OpenAI chat model) which generates the actual post content. The Agent has Memory attached to maintain context across runs and Tool access to extend its capabilities (e.g., formatting, fetching media, or calling a publishing API). Once the AI Agent produces the finished content, the workflow moves on to auto-post it to the target platform(s) — removing the need for manual copywriting or manual publishing, so new posts go out on a schedule or trigger without hands-on-keyboard work each time.
0
3
Lead & Contact Management System — Pipedrive Setup
Configured a clean, organized Pipedrive CRM structure to handle incoming leads and contacts efficiently. Built a streamlined People/Contacts view with custom filtering conditions, deal tracking (open vs. closed), and organization mapping — giving the client instant visibility into their pipeline health at a glance.
Result: Faster lead triage, zero missed follow-ups, and a CRM foundation ready to scale with automation.
0
10
Stop wasting time on repetitive emails. I build AI-powered CRM automations using n8n, Pipedrive, and OpenAI that instantly read incoming emails, generate personalized replies, update your CRM, and help you respond to every lead faster. Increase productivity, improve customer experience, and scale your business with smart automation.
For more details just contact me and discuss it. Thanks!
0
21
Solution:
I built an AI-powered RAG (Retrieval-Augmented Generation) chatbot agent in n8n that lets users chat naturally and get accurate, context-aware answers pulled directly from their own documents — not generic AI guesses.
How it works:
When a chat message is received, an AI Agent processes the query using a connected chat model and memory (to maintain conversation context). The agent uses a Pinecone vector store as a retrieval tool — searching embedded document data to pull the most relevant information before generating its response. This means every answer is grounded in real data, not hallucinated.
Result:
Turns any set of documents into an interactive, conversational knowledge base — users can ask questions and get instant, accurate answers instead of manually searching through files. This same architecture can be adapted for customer support bots, internal knowledge assistants, or document Q&A tools for any business.
Built with: n8n, Pinecone (vector database), AI Agent (LLM), conversational memory
1
32
Built an AI-powered RAG (Retrieval-Augmented Generation) agent using n8n that lets users ask questions and get instant summaries from any document. Files uploaded to Google Drive are automatically processed, chunked, and embedded into a Pinecone vector database — enabling accurate, context-aware Q&A instead of generic AI guesses. Turns hours of manual document review into seconds.
1
36