Phase-based blog creation system with specialized AI sub-agents
Needs changesWhat this workflow does
This AI workflow has 21 nodes and runs when a chat message arrives (plus 2 other triggers). Along the way it connects Google Sheets, Slack and Anthropic Chat Model.
How it runs
Trigger: When a chat message arrives (plus 2 other triggers).
- Orchestrator (AI Agent): runs an AI agent, with model: Claude; 10 tools (Do Research, Get Research, Call Blog Writer Agent, Call Hook Writer Agent…); memory: Simple Memory
- Headlines Writer (AI Agent): runs an AI agent
- Slack: uses Slack
- Research w/ Perplexity (HTTP Request): calls an HTTP API
- Save Research (Google Sheets): uses Google Sheets
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Orchestrator (v1.7), Headlines Writer (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
- Also check Slack Trigger requires a signing secret on the Slack API credential.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Orchestrator (v1.7), Headlines Writer (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (13)
- AI Agent
@n8n/n8n-nodes-langchain.agent - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - No Operation, do nothing
n8n-nodes-base.noOp - HTTP Request
n8n-nodes-base.httpRequest - Google Sheets Tool
n8n-nodes-base.googleSheetsTool - Google Sheets
n8n-nodes-base.googleSheets - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - AI Agent Tool
@n8n/n8n-nodes-langchain.agentTool - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Slack Trigger
n8n-nodes-base.slackTrigger - Slack
n8n-nodes-base.slack - Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic
From the author
Chat with a multi-agent system to write a blog. The orchestrator advances through research, headlines, hooks, outline, intro, draft, and final polish–one phase per reply—outputting options and asking you to proceed or rerun at each step. Who is this for?…