Luísa — AI Customer Service Agent with RAG by Daniele MaiaLuísa — AI Customer Service Agent with RAG by Daniele Maia

Luísa — AI Customer Service Agent with RAG

Daniele Maia

Daniele Maia

The problem

Customer service teams drown in repetitive questions, leads go cold outside business hours, and generic chatbots make things worse — they hallucinate answers and can't actually do anything.

What I built

Luísa is a production AI customer service agent. She answers from the business's real data via RAG, remembers each customer between conversations, books meetings directly into the calendar, and hands critical actions to a human for approval before anything irreversible happens.
RAG on business data — answers come from the company's own knowledge base, not from the model's imagination
Persistent memory — returning customers are recognized and context carries over
Scheduling — she checks availability and books meetings in the calendar (CRM + Calendar integration)
Human-in-the-loop — sensitive actions wait for human approval instead of running blind
Production-grade — error handling and monitoring, built with Claude + n8n

Try her live

Luísa is running in production right now — you can chat with her here: https://chat.dmaai.com.br

Stack

Claude (LLMs) · RAG · n8n · CRM + Calendar integrations · human-approval flows

Want something like this?

I build production AI agents and WhatsApp chatbots (official Meta Cloud API) end to end, from discovery to deploy.
Like this project

Posted Aug 4, 2026

Production AI agent: answers from business data via RAG, remembers customers, books meetings, human-in-the-loop on critical actions. Built with Claude + n8n.

Likes

0

Views

0