Generate deep research markdown reports with GPT, Tavily Search, and Google Sheets
Needs changesWhat this workflow does
This AI workflow has 32 nodes and runs when someone submits an n8n form. Along the way it connects OpenRouter Chat Model and Google Sheets.
How it runs
Trigger: When someone submits an n8n form.
- Plan Topics (AI Agent): runs an AI agent, with model: OpenRouter Chat Model; output parser: 5 Topics
- Intro (AI Agent): runs an AI agent, with model: OpenRouter Chat Model; output parser: Title, Intro, Chapters
- Split Out: splits a list into separate items
- Set Topics (Edit Fields (Set)): sets or maps fields
- Send Intro (Google Sheets): uses Google Sheets
- Merge: merges the data from its input branches
- Split Out: splits a list into separate items
- Merge: merges the data from its input branches
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Aggregate: combines items into one
…plus 15 more steps. See the full node list below.
Services it uses
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 Plan Topics (v1.8), Intro (v1.8), Sources (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) Plan Topics (v1.8), Intro (v1.8), Sources (v1.8), Table of Contents (v1.8), Writer5 (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (12)
- AI Agent
@n8n/n8n-nodes-langchain.agent - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Split Out
n8n-nodes-base.splitOut - Merge
n8n-nodes-base.merge - Edit Fields (Set)
n8n-nodes-base.set - Google Sheets
n8n-nodes-base.googleSheets - n8n Form Trigger
n8n-nodes-base.formTrigger - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - Aggregate
n8n-nodes-base.aggregate
From the author
This workflow generates deep researched report in markdown format and saves it in Google Sheet, that I then use for generating blogs for my website - Architjn Blogs How it works 1. User submits a search topic through a form. 2. AI generates five deep-dive…