Auto-reply to Udemy student Q&A with Mistral AI and Google Sheets
UnknownWhat this workflow does
This AI workflow has 22 nodes and runs on a schedule (every 30 minutes). Along the way it connects Google Sheets, Redis Chat Memory, Mistral Cloud Chat Model and Anthropic Chat Model and 4 more. It also calls udemy.com over HTTP.
How it runs
Trigger: On a schedule (every 30 minutes).
- Load Global Constants (Global Constants): uses Global Constants
- Fetch Unreplied Threads (Udemy API) (HTTP Request): calls udemy.com
- Split Threads Array (Split Out): splits a list into separate items
- Loop Through Each Thread (Loop Over Items (Split in Batches)): loops over the items in batches
- Fetch Full Thread History (HTTP Request): calls an HTTP API
- Skip if Instructor Sent Last Message (If): checks a condition and branches into true / false
- Log New Message to Sheet (Google Sheets): append
- Generate Redis Session Key (Code): runs custom JavaScript code
- AI Agent: runs an AI agent, with model: LLM: Mistral Large (Primary), LLM: Claude Sonnet 4.5 (Fallback); 1 tool (Tool: Jina Deep Research); memory: Memory: Redis Chat; output parser: Parser: Structured JSON Output
- Branch: Auto-Reply or Escalate? (If): checks a condition and branches into true / false
…plus 5 more steps. See the full node list below.
Services it uses
HTTP calls to: udemy.com
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that n8n-nodes-globals is verified or supports 3.0 (used in Load Global Constants).
Nodes used (17)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - Global Constants
n8n-nodes-globals.globalConstants - HTTP Request
n8n-nodes-base.httpRequest - Split Out
n8n-nodes-base.splitOut - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Google Sheets
n8n-nodes-base.googleSheets - If
n8n-nodes-base.if - Code
n8n-nodes-base.code - AI Agent
@n8n/n8n-nodes-langchain.agent - Redis Chat Memory
@n8n/n8n-nodes-langchain.memoryRedisChat - Mistral Cloud Chat Model
@n8n/n8n-nodes-langchain.lmChatMistralCloud - Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic - Jina Ai Tool
n8n-nodes-base.jinaAiTool - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Gmail
n8n-nodes-base.gmail - Merge
n8n-nodes-base.merge
From the author
Stop Drowning in Repetitive Udemy Student Questions If you teach on Udemy at any meaningful scale, you already know the problem: 80% of student messages are variations of the same handful of questions, but every one of them needs a thoughtful reply to keep…