Build an intelligent agent that learns and responds automatically
Workflow Description
An advanced template that creates a smart agent receiving inquiries via chat, processing them using state-of-the-art language models, maintaining conversation context, distributing tasks in batches, and extracting information from external sources to provide accurate responses.
How it works
- 1.Receive message via activated chat trigger
- 2.Process text using LLM chain with Open Router model
- 3.Store previous context in buffer memory
- 4.Split large tasks into small batches for processing
- 5.Invoke external tools such as Wikipedia for research
Use cases
- Build a smart assistant that answers customer questions with historical context
- Create a multi-task agent that distributes requests and handles them sequentially
Requirements
- Valid API key for Open Router
- Memory settings configured to store context between conversations
- Available web tools for search and data extraction
Service Value
Ideal as a smart automation service combining integrations and AI to produce ready-to-use results.
Apps Used
Details
How to Use
- 1.Click "Download Template"
- 2.Open your n8n dashboard
- 3.Go to Workflows > Import from File
- 4.Select downloaded file and configure credentials
Nodes Used (17)
Chat Message Trigger
Chat Trigger
Generate Search Queries using LLM
LLM Chain
LLM Response Provider (OpenRouter)
Lm Chat Open Router
Parse and Chunk JSON Data
Code
Perform SerpAPI Search Request
HTTP Request
Perform Jina AI Analysis Request
HTTP Request
Format SerpAPI Organic Results
Code
Extract Relevant Context via LLM
Agent
Generate Comprehensive Research Report
Agent
Split Data for SerpAPI Batching
Split In Batches
Split Data for Jina AI Batching
Split In Batches
LLM Memory Buffer (Input Context)
Memory Buffer Window
LLM Memory Buffer (Report Context)
Memory Buffer Window
Fetch Wikipedia Information
Tool Wikipedia
Sticky Note: SerpAPI Setup
Sticky Note
Sticky Note: Jina AI Setup
Sticky Note
Sticky Note: OpenRouter API Setup
Sticky Note