Generate multi-agent research reports with Tavily, Groq, Notion and Supabase

Go to Workflow
0 views
Built by Redowan Ahmed Farhan Redowan Ahmed Farhan
Created on June 10, 2026

Description

How it works
A manual trigger sets the research topic and generates three parallel Tavily web search queries
A Summarizer Agent (Groq Llama 3.3 70B) and an Analyst Agent (OpenRouter GPT) process the search results simultaneously, producing a factual summary and a deep trend analysis
A Synthesis Agent (Groq Llama 3.3 70B) combines both outputs into a structured executive report with key findings, strategic implications, and recommended actions
The report is chunked and saved as a new Notion database page, then embedded with OpenAI and indexed in Supabase for semantic search

Set up steps
Add your Tavily, Groq, and OpenRouter API credentials (~10 min)
Connect Notion OAuth2 and point the node to your target database
Add your Supabase credentials and confirm your documents table has a vector column

Nodes Used (10)

AI Agent
@n8n/n8n-nodes-langchain.agent
Code
n8n-nodes-base.code
Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader
Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi
Groq Chat Model
@n8n/n8n-nodes-langchain.lmChatGroq
HTTP Request
n8n-nodes-base.httpRequest
Notion
n8n-nodes-base.notion
OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter
Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter
Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase