I built an AI-powered chatbot that answers customer questions using ONLY real data from a busines...

I built an AI-powered chatbot that answers customer questions using ONLY real data from a busines...I built an AI-powered chatbot that answers customer questions using ONLY real data from a busines...

The network for creativity

Join 1.25M professional creatives like you

Connect with clients, get discovered, and run your business 100% commission-free

Creatives on Contra have earned over $150M and we are just getting started

Back to feedPost

Muhammad Usama Manzoor

• Jul 27

I built an AI-powered chatbot that answers customer questions using ONLY real data from a business's own website — no hallucinations, no generic AI guesses.

Most AI chatbots businesses deploy today have one major flaw: they make things up. A customer asks about a return policy, and the bot confidently gives a wrong answer. That's a trust problem, not just a technical one.

So I built a Retrieval-Augmented Generation (RAG) chatbot that solves this directly.

📌 How it works: ✅ Scrapes and processes real website content (products, policies, FAQs) ✅ Converts that content into a searchable knowledge base using vector embeddings ✅ Retrieves only the most relevant information before answering — grounded, not guessed ✅ Transparently says "I don't have that information" instead of fabricating an answer when it's outside its knowledge

🔧 Built with: n8n (workflow automation) | Google Gemini (LLM + embeddings) | Vector Database (RAG retrieval)

This is the kind of AI agent businesses actually need for customer support automation — accurate, on-brand, and safe to put in front of real customers. Watch the full demo below

I'm currently building hands-on expertise in AI agent development and workflow automation — including chatbots, lead qualification systems, and WhatsApp/CRM integrations using n8n. Currently taking on freelance automation projects — feel free to DM me or check the link in my profile.

AI Agent Development AI Automation Web Scraping Google Gemini N8N

OLAJUMOKE ADEYOJU

• Jul 29

Automate your business, eliminate repetitive tasks, and save hours every week with custom AI workflow automation. I build intelligent automation systems that connect your favorite apps, streamline operations, and help your business run faster with minimal manual work.

#AIAutomation #WorkflowAutomation #BusinessAutomation #ArtificialIntelligence #NoCode #Automation #Zapier #Make #n8n #GoogleSheets #HubSpot #Notion #Shopify #Slack #CRM #Productivity #DigitalTransformation #SmallBusiness #Entrepreneur #BusinessGrowth

AgentKit Gmail Google Sheets AI Automation

Gabriel Gabriel

• Jul 29

Are you looking to build a powerful AI agent that can understand users, remember conversations, connect with your data, and operate like a personalized digital companion? Many businesses struggle with creating AI agents that go beyond simple chatbots because they need memory, custom personality, integrations, reliable deployment, and continuous optimization.

I build and deploy custom ElizaOS AI agents with Replika-style conversational experiences, personalized behavior, long-term memory, and real-world integrations. I can configure AI personalities, connect knowledge sources, integrate Notion workspaces, build API connections, and deploy production-ready agents that run securely 24/7.

My technology stack includes ElizaOS, TypeScript, Node.js, GitHub, VS Code, Cursor, pnpm, Docker, PM2, Hetzner VPS, Ubuntu, Notion API, Supabase, Pinecone, OpenAI API, Google Gemini API, Telegram Bot API, X Developer API, Postman, Cloudflare, Langfuse, LangSmith, Arize Phoenix, DeepEval, n8n, Zapier, and secure credential management tools.

Whether you need an AI companion, business assistant, knowledge agent, or custom automation system, I deliver a complete solution from development to deployment with scalable architecture and reliable performance.

langchainagent replikastylebot elizaosagent

YASH GOYAL

• Jul 29

Businesses lose customers to unanswered WhatsApp messages, and the questions are nearly always the same.

I built Axon where teams design their WhatsApp conversation visually on a drag-and-drop canvas, publish it to a live number, and let AI answer anything the script missed, inside a persona they define. Non-technical staff edit the bot in minutes, no developer needed.

Includes a shared team inbox with human handoff, analytics showing which question loses customers, and a simulator that runs the real bot with no WhatsApp account, so clients test before paying for Meta or Twilio setup.