This automation template solves the challenge of personalized customer support for owners of multiple websites requiring accurate, context-aware responses about services, packages, and policies. It’s ideal for businesses managing several domains with unique content but a unified support logic.
## Who it´s for
- Owners of multiple author portfolio websites seeking automated support.
- Publishing companies offering ghostwriting and book publication services.
- SaaS products with complex pricing and policies needing precise client assistance.
- Chatbots requiring long-term conversation memory across different domains.
## What the automation does
- Receives user queries via HTTP webhook with site, page, and userId.
- Routes the request to a specific AI agent based on the provided site.
- Uses OpenRouter LLM and retrieves contextual data from Pinecone vector stores (by namespace).
- Loads chat history from PostgreSQL using userId to maintain dialogue continuity.
- Returns a structured JSON response through Respond to Webhook.
## What´s included
- Ready-to-use n8n workflow with LangChain agents.
- Logic for routing requests by site and selecting the appropriate agent.
- Integrations with HTTP API, Pinecone, PostgreSQL, OpenRouter, and Cohere.
- Basic text instructions for deployment and adaptation.
## Requirements for setup
- n8n instance with workflow execution access.
- Pinecone account (for vector knowledge storage), PostgreSQL (for chat history), OpenRouter (for LLM inference).
- Cohere account (optional, for embeddings if used).
- Valid API keys for all listed services.
## Benefits and outcomes
- Unified support system across multiple sites with shared logic.
- Accurate answers based on up-to-date knowledge in vector databases.
- Persistent chat memory across sessions via PostgreSQL.
- Fast onboarding of new services — just update Pinecone data.
- Scalable: easily add new sites and agents.
- Reduced manual support load by automating common inquiries.
## Important: template only
Important: you are purchasing a ready-made automation workflow template only. Rollout into your infrastructure, connecting specific accounts and services, 1:1 setup help, custom adjustments for non-standard stacks and any consulting support are provided as a separate paid service at an individual rate. To discuss custom work or 1:1 help, contact via Telegram: @gleb923.
AI support assistant
HTTP webhook
multiple websites
vector knowledge bases
Pinecone vector store
chat memory
PostgreSQL chat history
OpenRouter LLM
n8n workflow
context-aware response
query processing via API
support with vector search
personalized chatbot
LangChain agent
services and packages
refund policies
customer support automation
agent without retraining
No feedback yet