#customer-support

Production-grade FastAPI microservice that triages support tickets into validated, structured JSON using OpenAI Native Structured Outputs.

AI-powered multilingual customer support automation built using n8n, Groq API, Telegram Bot API.

AI chatbot widget for React, Next.js, Vue, Angular, and vanilla JS. Scrape your website, train a chatbot, embed in 60 seconds. Free tier: 50 messages/month. By Aparsoft.

Production-grade AI Customer Support Agent — WhatsApp, Telegram & Web

Customer support operations agent on LangGraph — ticket triage, knowledge lookup, and escalation flows

AI-powered customer support chatbot for North Star outdoor gear store

White-label multi-workspace support chatbot with self-hosted voice: talk to your bot, hear it answer — Next.js 15 + local RAG (sqlite-vec) + faster-whisper STT + Kokoro/Coqui TTS, multi-language

AI-powered FAQ chatbot with semantic search — understands meaning, not just keywords. Built with Streamlit, sentence-transformers, ChromaDB, and Groq LLM. Features a dynamic, hot-reloadable system prompt, two-sided chat UI, and guideline-driven handling of small talk, off-topic questions, and safety edge cases.

AI support assistant with intent routing, RAG, conversation memory, citations, and human escalation.

AI support agent demo — RAG over a knowledge base with automatic escalation to a human (Python, Flask, Claude API)

AI-powered customer support agent using intent classification, semantic retrieval, Gemini-based grounded responses, and escalation handling.

Sequential specialized-agent customer support workflow built with CrewAI.

Asyntai AI Chatbot for Flow Launcher: read your website chats, leads and tickets, and ask your own AI chatbot, from the Flow Launcher search box.

Refund triage agent: reads a refund email, looks up the order, applies a written policy, drafts the reply; staff approve every send. 531 synthetic tickets, 4 languages. MSc DSAIB, HEC Paris. Sole author: Louan Bardou.

🌸 AI-powered customer support agent for Bloom Aesthetics Clinic — built with OpenAI GPT-4o. Handles FAQ answering, lead qualification, escalation detection, and conversation summarisation using a structured SOP. Pure Python, no frameworks.

AI-powered customer support chatbot built with Node.js, Express, JavaScript, and OpenAI API.

AI-powered customer support system that classifies tickets, detects sentiment and urgency, retrieves knowledge using RAG, routes requests, and automates customer support workflows with n8n and OpenAI.

SupportPilot AI — an AI support agent for small businesses: train it on your own docs, drop one script tag on your site, and it answers customers 24/7 with sources. .NET 8 + React, offline brain built in, OpenAI optional, Stripe billing.

My latest flagship project — a multi-tenant RAG customer-support SaaS. Upload your docs, embed one line of code, and let AI answer customer questions with citations. Built with Next.js 16, React 19, FastAPI, PostgreSQL + pgvector, Voyage embeddings, Clerk auth, and Anthropic Claude.

n8n AI customer support and lead assistant using OpenAI, Google Sheets mock store data, Telegram alerts, and a webhook interface.

Agentic customer care bot that resolves problems with real actions — confirm-gated refunds, hybrid vector+graph knowledge, emotional tone adaptation, cross-session memory, and graceful human handoff. Dual-provider LLM (Gemini + Claude Haiku).

Autonomous AI Support Agent for AppleSupport featuring Llama 3.1 Few-Shot Intent Classification, Grounded Vector RAG Retrieval with Citations, Hybrid Risk Escalation Engine, and Streamlit Demo UI.

Multi-agent AI customer support system — Pinecone hybrid RAG, SLA-aware ticketing, and RAGAS evaluation on FastAPI + Streamlit

Zendesk MCP for Cursor, VS Code, Antigravity, Bob IDE & Claude — 14 ticket tools. npx @markusvankempen/zendesk-mcp-server · pip install zendesk-mcp-server-py · IBM Code Engine SSE