Deep research agent - automated research & Notion report builder
Needs changesWhat this workflow does
This AI workflow has 36 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects OpenAI, Notion, Google Gemini Chat Model and OpenRouter Chat Model. It also calls api.tavily.com over HTTP.
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- Strategy Agent (AI Agent): runs an AI agent, with model: OpenRouter Chat Model; memory: Simple Memory; output parser: Structured Output Parser
- Switch: routes items into 2 branches
- Respond to Webhook: sends the response back to the webhook caller
- Respond to Webhook: sends the response back to the webhook caller
- Code: runs custom JavaScript code
- OpenAI: uses OpenAI
- Notion: work with database page
- Search Query Agent (AI Agent): runs an AI agent, with model: OpenRouter Chat Model; output parser: Structured Output Parser
- Split Out: splits a list into separate items
- Loop Over Queries (Loop Over Items (Split in Batches)): loops over the items in batches
…plus 18 more steps. See the full node list below.
Services it uses
HTTP calls to: api.tavily.com
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Strategy Agent (v1.8), Search Query Agent (v1.8), Report Agent (v1.8): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Strategy Agent (v1.8), Search Query Agent (v1.8), Report Agent (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (19)
- Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Switch
n8n-nodes-base.switch - AI Agent
@n8n/n8n-nodes-langchain.agent - Split Out
n8n-nodes-base.splitOut - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - HTTP Request
n8n-nodes-base.httpRequest - Edit Fields (Set)
n8n-nodes-base.set - OpenAI
@n8n/n8n-nodes-langchain.openAi - Aggregate
n8n-nodes-base.aggregate - Notion
n8n-nodes-base.notion - Markdown
n8n-nodes-base.markdown - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Filter
n8n-nodes-base.filter - Code
n8n-nodes-base.code - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - Webhook
n8n-nodes-base.webhook - Respond to Webhook
n8n-nodes-base.respondToWebhook
From the author
Overview - This workflow acts as an AI-powered research assistant that takes a topic from the user, performs multi-step intelligent research, and stores the final report in Notion. It uses advanced search, content extraction, and AI summarization to deliver a…