Triage and retry failed workflow executions with Anthropic, Jira and OpenTelemetry
Ready for 3.0What this workflow does
This AI workflow has 15 nodes and runs when another workflow fails (error workflow). Along the way it connects Jira Software and Anthropic Chat Model.
How it runs
Trigger: When another workflow fails (error workflow).
- Extract Error Details (Code): runs custom JavaScript code
- Root-Cause Analysis Agent (Basic LLM Chain): sends a prompt to an LLM, with output parser: Parse Structured Output
- Combine Diagnostics and Telemetry (Code): runs custom JavaScript code
- Prepare Fallback for AI Failure (Code): runs custom JavaScript code
- Check Retry Eligibility (If): checks a condition and branches into true / false
- Log in Jira - Diagnostics Failed (Jira Software): uses Jira Software
- Compute Retry Backoff (Code): runs custom JavaScript code
- Log in Jira - No Retry (Jira Software): uses Jira Software
- Send OTel Span to Collector (HTTP Request): calls an HTTP API (POST)
- Wait: pauses before continuing
…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 (9)
- Jira Software
n8n-nodes-base.jira - HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - Wait
n8n-nodes-base.wait - If
n8n-nodes-base.if - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Error Trigger
n8n-nodes-base.errorTrigger
From the author
Quick overview This workflow triggers on n8n execution errors, uses Anthropic (Claude) to classify the failure as transient or logic, and then either retries the failed execution via the n8n API with exponential backoff or creates a Jira issue, while also…