Find wasted Meta ad spend by placement, region, age and hour with Claude

by Nocode Expert ✓ · 75 views · created 2026-07-11 · Market Research, AI Summarization

What this workflow does

This workflow has 13 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Facebook Graph API. It also calls api.anthropic.com over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow”.

1. Set config: result events, floor (Code): runs custom JavaScript code
2. Fetch account totals (Meta) (Facebook Graph API): uses Facebook Graph API
3. Compute benchmark (Code): runs custom JavaScript code
4. List delivery breakdowns (Code): runs custom JavaScript code
5. Fetch breakdown insights (Meta) (Facebook Graph API): uses Facebook Graph API
6. Flatten & score slices (Code): runs custom JavaScript code
7. Flag underperforming slices vs benchmark (Code): runs custom JavaScript code
8. Any budget at risk? (If): checks a condition and branches into true / false
9. Build AI prioritization prompt (Code): runs custom JavaScript code
10. Print — nothing to cut (Code): runs custom JavaScript code

…plus 2 more steps. See the full node list below.

Services it uses

Facebook Graph API

HTTP calls to: api.anthropic.com

Before you upgrade to n8n 3.0

Nodes used (5)

• Manual Triggern8n-nodes-base.manualTrigger
• Coden8n-nodes-base.code
• HTTP Requestn8n-nodes-base.httpRequest
• Facebook Graph APIn8n-nodes-base.facebookGraphApi
• Ifn8n-nodes-base.if

From the author

Quick overview This workflow pulls the last 30 days of Meta Ads insights across multiple breakdowns, calculates an account cost-per-result benchmark, flags high-waste delivery slices, and uses Anthropic Claude to rank a prioritized “kill list” with…

View the original on n8n.io → Check your own copy