Gemini-powered Facebook comment & DM assistant with Notion
Ready for 3.0What this workflow does
This AI workflow has 23 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects Google Gemini Chat Model, Facebook Graph API and Notion. It also calls api.notion.com over HTTP.
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- If: checks a condition and branches into true / false
- Parse Comms (Edit Fields (Set)): sets 8 fields: page_id, post_id, comment_id…
- Code: runs custom JavaScript code
- Check Database (Notion): get many (database page)
- Fetch KB (HTTP Request): calls api.notion.com (POST)
- Arrange KB (Code): runs custom JavaScript code
- Who's there? (If): checks a condition and branches into true / false
- Comment (Facebook Graph API): uses Facebook Graph API
- AI Agent: runs an AI agent, with model: Google Gemini Chat Model
- Separate rep&sent (Edit Fields (Set)): sets 2 fields: sentiment, dm_message
…plus 11 more steps. See the full node list below.
Services it uses
HTTP calls to: api.notion.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 (9)
- AI Agent
@n8n/n8n-nodes-langchain.agent - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Facebook Graph API
n8n-nodes-base.facebookGraphApi - Webhook
n8n-nodes-base.webhook - Edit Fields (Set)
n8n-nodes-base.set - Notion
n8n-nodes-base.notion - HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - If
n8n-nodes-base.if
From the author
What Problem Does It Solve? Customers often ask product questions or prices in comments. Businesses waste time replying manually, leading to delays. Some comments only need a short thank-you reply, while others need a detailed private response. This workflow…