Human in the Loop (Gmail) is capricious

[AyS_0908]

Hi,
I am creating a “content generation” flow:

1. Search latest news → Propose 3 topics
2. Human in the Loop (Gmail): choose a topic
3. Generate article + image
4. Human in the Loop (Gmail): content validation
5. If human is positive → Storage on Sheet + Publication on Linkedin
   5bis. If human is negative → Rework content

Describe the problem/error/question

Issue 1: In Step 5bis the article is not rewritten → it is the same which is proposed after the loop.

Issue 2: I wonder if my flow is not much too complicated (I am an old beginner on n8n)

Thanks in advance for your help!

Share the output returned by the last node

When the switch requires to rework the article: I obtain the same article than previously

Information on your n8n setup

• n8n version: Latest
• Database (default: SQLite): SQLlite
• n8n EXECUTIONS_PROCESS setting (default: own, main): own
• Running n8n via (Docker, npm, n8n cloud, desktop app): docker
• Operating system: windows

[krisn0x]

Hey there!

2 questions:

• You are sending a rework instruction + the article to be reworked in that second AI node right? Not just the article text?
• Can you copy the Check node before the second AI and paste it here, so I can view the logic there?

[AyS_0908]

Hey @krisn0x , thank you for your response.

Herebelow the code of this part of my flow, where, yes, I provide both the former article + the instruction coming from the “Gmail/Human In the Loop”.

Thanks again