Automate competitor research with Exa.ai, Notion and AI agents
Needs changesWhat this workflow does
This AI workflow has 30 nodes and runs manually, when you click “Execute workflow”. Along the way it connects OpenAI Chat Model, HTTP Request and Notion. It also calls api.exa.ai, api.firecrawl.dev and serpapi.com over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Set Source Company (Edit Fields (Set)): sets 1 field: company_url
- Competitor Search via Exa.ai (HTTP Request): calls api.exa.ai (POST)
- Results to List (Split Out): splits a list into separate items
- Extract Domain (Edit Fields (Set)): sets 2 fields: title, url
- Remove Duplicates: removes duplicate items
- Limit: keeps the first few items
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Company Overview Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 6 tools (Search LinkedIn, Get Company News, Search WellFound, Webscraper Tool…); output parser: Structured Output Parser
- Company Product Offering Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 2 tools (Webscraper Tool, Search Company Website); output parser: Structured Output Parser
- Company Product Reviews Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 2 tools (Webscraper Tool, Search Product Review Sites); output parser: Structured Output Parser
…plus 3 more steps. See the full node list below.
Services it uses
HTTP calls to: api.exa.ai, api.firecrawl.dev, serpapi.com
Uses Firecrawl. New users get 10% off with our link.
Before you upgrade to n8n 3.0
2 things in this workflow are removed in n8n 3.0. Fix them before you upgrade:
- HTTP Request Tool (legacy) in Search Crunchbase, Search WellFound, Search LinkedIn…: replace with HTTP Request node connected to the AI Agent's Tool input.
- AI Agent v1 (old agent modes) in Company Overview Agent (v1.6), Company Product Offering Agent (v1.6), Company Product Reviews Agent (v1.6): 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 |
|---|---|
| HTTP Request Tool (legacy) Search Crunchbase, Search WellFound, Search LinkedIn, Webscraper Tool1, Check Company Profiles Exist, Webscraper Tool, Search Company Website, Search Product Review Sites, Webscraper Tool2, Get Company News | HTTP Request node connected to the AI Agent's Tool input |
| AI Agent v1 (old agent modes) Company Overview Agent (v1.6), Company Product Offering Agent (v1.6), Company Product Reviews Agent (v1.6) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (13)
- Manual Trigger
n8n-nodes-base.manualTrigger - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - HTTP Request Tool
@n8n/n8n-nodes-langchain.toolHttpRequest - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Remove Duplicates
n8n-nodes-base.removeDuplicates - Edit Fields (Set)
n8n-nodes-base.set - Split Out
n8n-nodes-base.splitOut - Notion
n8n-nodes-base.notion - Limit
n8n-nodes-base.limit - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - HTTP Request
n8n-nodes-base.httpRequest - Wait
n8n-nodes-base.wait - AI Agent
@n8n/n8n-nodes-langchain.agent
From the author
This n8n workflow demonstrates a simple multi-agent setup to perform the task of competitor research. It showcases how using the HTTP request tool could reduce the number of nodes needed to achieve a workflow like this. How it works For this template, a…