Generate riddle shorts & post on YouTube with Sonnet 3.5, Pinecone & Creatomate
Needs changesWhat this workflow does
This AI workflow has 27 nodes and runs on a schedule (every day). Along the way it connects Anthropic Chat Model, Embeddings OpenAI, Pinecone Vector Store and Google Sheets and 1 more.
How it runs
Trigger: On a schedule (every day).
- Riddle generation AI Agent (AI Agent): runs an AI agent, with model: Anthropic Chat Model; 1 tool (Vector Store to Find Previous Riddles); output parser: Structured Output Parser
- Fetch Audio From Sheet (Ensuring Rotation) (Google Sheets): uses Google Sheets
- Convert Riddles JSON to 1 Text item for Vector Insertion (Code): runs custom JavaScript code
- Merge: merges the data from its input branches
- Insert Riddles to Vector Store (Pinecone Vector Store): uses the Pinecone vector store, with embeddings: Embeddings OpenAI; document loader: Default Data Loader
- Render Youtube Short (HTTP Request): calls an HTTP API
- Fetch Current Shorts Title (Numbered) (Google Sheets): uses Google Sheets
- Wait: pauses before continuing
- Calculate Next Shorts Title Number (To update at the end) (Code): runs custom JavaScript code
- Youtube Upload HTTP request Setup (HTTP Request): calls an HTTP API
…plus 9 more steps. See the full node list below.
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 Riddle generation AI Agent (v1.9): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
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) Riddle generation AI Agent (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (15)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Merge
n8n-nodes-base.merge - Wait
n8n-nodes-base.wait - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - If
n8n-nodes-base.if - AI Agent
@n8n/n8n-nodes-langchain.agent - Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone - Google Sheets
n8n-nodes-base.googleSheets - Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Gmail
n8n-nodes-base.gmail
From the author
This workflow allows you to generate riddle-themed vertical videos (9:16), render them using Creatomate, and upload them directly to YouTube — all automatically. It's optimized for low-cost operation while still integrating AI and automation at key stages.…