Generate multi-agent research reports with Tavily, Groq, Notion and Supabase
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 22 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Groq Chat Model, OpenRouter Chat Model, Notion and Supabase Vector Store and 1 more. It also calls api.tavily.com over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Set Research Topic (Edit Fields (Set)): sets 3 fields: topic, depth, session_id
- Parse Orchestrator Tasks (Code): runs custom JavaScript code
- Web Search Query (HTTP Request): calls api.tavily.com (POST)
- Web Search Query (HTTP Request): calls api.tavily.com (POST)
- Web Search Query (HTTP Request): calls api.tavily.com (POST)
- Merge: merges the data from its input branches
- Aggregate Research Context (Code): runs custom JavaScript code
- Summarizer Sub-Agent (AI Agent): runs an AI agent, with model: Summarizer LLM
- Analyst Sub-Agent (AI Agent): runs an AI agent, with model: OpenAi Analyst LLM
- Combine Agent Outputs (Merge): merges the data from its input branches
…plus 5 more steps. See the full node list below.
Services it uses
HTTP calls to: api.tavily.com
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (13)
- Manual Trigger
n8n-nodes-base.manualTrigger - Groq Chat Model
@n8n/n8n-nodes-langchain.lmChatGroq - Code
n8n-nodes-base.code - Edit Fields (Set)
n8n-nodes-base.set - HTTP Request
n8n-nodes-base.httpRequest - Merge
n8n-nodes-base.merge - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - Notion
n8n-nodes-base.notion - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter
From the author
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…