Retry flaky HTTP calls with Google Gemini and Google Sheets dead letters
Ready for 3.0What this workflow does
This AI workflow has 17 nodes and runs when another workflow calls it (plus 1 other trigger). Along the way it connects Google Sheets and Google Gemini Chat Model.
How it runs
Trigger: When another workflow calls it (plus 1 other trigger).
- Start the Attempt Counter (Code): runs custom JavaScript code
- Load the Dead Letter Register (Google Sheets): uses Google Sheets
- Call the Service (HTTP Request): calls an HTTP API
- Pick What Is Worth Another Try (Code): runs custom JavaScript code
- Report Success (Code): runs custom JavaScript code
- Triage the Failure (Basic LLM Chain): sends a prompt to an LLM, with model: Gemini for Triage; output parser: Triage Schema
- Was This a Replay (If): checks a condition and branches into true / false
- Count It and Decide (Code): runs custom JavaScript code
- Close It in the Register (Google Sheets): append or update
- Retry or Give Up (Switch): routes items into 2 branches
…plus 3 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 (11)
- Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Google Sheets
n8n-nodes-base.googleSheets - If
n8n-nodes-base.if - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Switch
n8n-nodes-base.switch - Wait
n8n-nodes-base.wait
From the author
Quick Overview This workflow makes unreliable HTTP requests safer by using Google Gemini to classify failures, retry only transient errors with exponential backoff, and log non-retriable or exhausted failures to a Google Sheets dead-letter register that is…