Meta Ads Performance Analysis with GPT-4 & Gemini AI Comparisons
Ready for 3.0What this workflow does
This AI workflow has 21 nodes and runs on a schedule (every day). Along the way it connects Facebook Graph API, Google Gemini Chat Model, Google Sheets and OpenAI.
How it runs
Trigger: On a schedule (every day).
- Set parameters (Edit Fields (Set)): sets 3 fields: source, campaign_id, benchmarks_data
- If: checks a condition and branches into true / false
- Get Ads (Facebook Graph API): uses Facebook Graph API
- Get Ads from Sheet (Google Sheets): uses Google Sheets
- Ads Split Out (Split Out): splits a list into separate items
- Get Ad Details (Facebook Graph API): uses Facebook Graph API
- Get Insights (Facebook Graph API): uses Facebook Graph API
- Merge: merges the data from its input branches
- Insights Split Out (Split Out): splits a list into separate items
- Prepare CSV for OpenAI (Code): runs custom JavaScript code
…plus 8 more steps. See the full node list below.
Services it uses
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 (12)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - Facebook Graph API
n8n-nodes-base.facebookGraphApi - Split Out
n8n-nodes-base.splitOut - Edit Fields (Set)
n8n-nodes-base.set - If
n8n-nodes-base.if - Merge
n8n-nodes-base.merge - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Code
n8n-nodes-base.code - Google Sheets
n8n-nodes-base.googleSheets - OpenAI
@n8n/n8n-nodes-langchain.openAi - AI Agent
@n8n/n8n-nodes-langchain.agent
From the author
This workflow transforms raw Meta Ads data into actionable, expert-level insights. It acts as a virtual performance marketer, analyzing each creative's performance, comparing it against your historical benchmarks, and delivering clear recommendations on…