All Agents
🎧
Customer SupportLive

AI Support Agent

Multi-Channel AI Customer Support for $85/mo

  • 📨WhatsApp, Telegram, Email & Web Chat — one AI brain
  • 📚RAG knowledge base — AI only answers from your docs
  • 🛡️3-layer anti-hallucination guardrails
  • 💰$85/mo vs $990+ on Intercom or Zendesk

4

Channels

<2s

Avg Response

$85

Cost/mo

80%

AI Resolution

A

AI Support Agent

AI Shopping Assistant

Live
Ask about any product...
Voice Chat

"Show me trending sneakers"

Message Flow (8 Steps)

From incoming message to AI response — across any channel.

1

Customer sends a message via WhatsApp, Telegram, Email, or Web Chat

2

Django backend normalizes it into a UnifiedMessage format

3

Claude Haiku classifies the ticket (billing, technical, account, general)

4

Escalation check: low confidence, negative sentiment, or human request?

5

pgvector searches your knowledge base for the top 3 relevant chunks

6

Claude Sonnet generates a response constrained to KB context only

7

3-layer guardrails scan for hallucinated prices, policies, or guarantees

8

Response sent back through the original channel

architecture

Incoming Channels

WhatsApp

Cloud API v22.0

Email

Gmail OAuth2

Telegram

Bot API

Web Chat

WebSocket

Normalize to UnifiedMessage

Django Backend

DRF + Django Channels + Daphne

Classify

Claude Haiku

Ticket classification — $1/M tokens

Escalation check

Normal Path (80%)

pgvector Search

Cosine similarity — top 3 KB chunks

Claude Sonnet

Response generation — $3/M tokens

Guardrails Scan

3-layer anti-hallucination check

Reply via original channel

Escalation Path (20%)

Escalation Detector

Confidence < 0.7 | Sentiment | Human request

Handoff Package

AI summary + suggested response

Human Agent

Takes over with full context

Operations

Dashboard

Next.js 15 + Tailwind

Knowledge Base

Upload & manage docs

Analytics

AI vs human resolution

Team Settings

Multi-tenant + roles

Built for Real Support Teams

Everything you need to run AI-powered customer support in production.

📨

4-Channel Inbox

WhatsApp, Telegram, Email (Gmail), and Web Chat — all normalized into a single UnifiedMessage format. One AI brain handles every channel.

📚

RAG Knowledge Base

Upload your docs (.md, .txt, .pdf). Auto-chunked with smart boundary detection, embedded with OpenAI, and searched via pgvector cosine similarity. AI only answers from your KB.

🧠

Dual-Model AI

Claude Haiku for fast ticket classification (billing, technical, account, general). Claude Sonnet for high-quality response generation with strict guardrails.

🛡️

3-Layer Anti-Hallucination

System prompt constraints + empty RAG fallback + post-generation scan for sensitive patterns (prices, refund policies, SLAs). No fabricated answers.

🚨

Smart Escalation

Three triggers: low AI confidence (<0.7), negative sentiment (weighted keyword scoring), or customer requests a human. Clean handoff with AI summary + suggested response.

📊

Full Dashboard

Ticket queue with filters, conversation view with AI sidebar, analytics (AI vs human resolution rates), knowledge base manager, canned responses, and channel settings.

Who It's For

Built for teams that want 24/7 support without the $990/mo price tag.

Small businesses replacing expensive support tools like Intercom ($990/mo) or Zendesk ($1,500/mo)

Startups needing 24/7 customer support without hiring a full team

E-commerce stores automating billing, shipping, and product FAQ responses

SaaS companies handling technical support and account questions

Agencies building white-label support solutions for clients

Production Stack

Django + Claude AI + pgvector — battle-tested and self-hosted.

Django + DRFBackend
Django Channels + DaphneBackend
Next.js 15Frontend
Tailwind CSSFrontend
Claude Haiku (Classification)AI / ML
Claude Sonnet (Responses)AI / ML
OpenAI EmbeddingsAI / ML
PostgreSQL + pgvectorDatabase
RedisInfrastructure
Docker ComposeInfrastructure

Deploy in 6 Steps

One Docker Compose command gets you from zero to live support agent. Full details in the GitHub README.

1

Clone the repository

$git clone https://github.com/codewithmuh/ai-support-agent.git && cd ai-support-agent
2

Configure environment variables

Add your API keys: Anthropic (Claude), OpenAI (embeddings), and channel credentials (WhatsApp, Gmail, Telegram)

$cp .env.example .env
3

Start with Docker Compose

Starts PostgreSQL + pgvector, Redis, Django backend (Daphne), and Next.js dashboard

$docker compose up -d --build
4

Upload your knowledge base

Go to localhost:3000/knowledge-base, upload your support docs (.md, .txt, .pdf). The system auto-chunks and embeds them.

5

Configure channels

Dashboard Settings page — add your WhatsApp Cloud API credentials, Gmail OAuth, and Telegram bot token. All configured via UI.

6

Test it

Send a message on any connected channel. Watch the AI classify, search your KB, and respond. Try triggering an escalation with an angry message.

Ready to replace your support tool?

Deploy the AI Support Agent on your own server. Open source, 4 channels, $85/mo instead of $990+. One Docker Compose command.

Built by CodeWithMuh