Generate email newsletters from Telegram keywords with Dumpling AI and GPT
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 14 nodes and runs on Telegram events (message). Along the way it connects HTTP Request, Telegram, OpenAI Chat Model and OpenAI and 1 more. It also calls app.dumplingai.com over HTTP.
How it runs
Trigger: On Telegram events (message).
- AI Agent: runs an AI agent, with model: LLM: Language Model; 2 tools (Search_news, Google_autocomplete); memory: Simple Memory; output parser: Parser: Format News JSON
- Split Articles (Split Out): splits a list into separate items
- Loop: Process Each Article (Loop Over Items (Split in Batches)): loops over the items in batches
- Aggregate: combines items into one
- Wait: pauses before continuing
- Generate Newsletter (OpenAI): uses OpenAI
- Scraper: Clean Article Content (HTTP Request): calls app.dumplingai.com (POST)
- Send Newsletter via Email (Gmail): uses Gmail
Services it uses
HTTP calls to: app.dumplingai.com
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 AI Agent: Expand Keyword & Orchestrate Tools (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) AI Agent: Expand Keyword & Orchestrate Tools (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (13)
- Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Http Request Tool
n8n-nodes-base.httpRequestTool - Wait
n8n-nodes-base.wait - Telegram Trigger
n8n-nodes-base.telegramTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Split Out
n8n-nodes-base.splitOut - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - HTTP Request
n8n-nodes-base.httpRequest - Aggregate
n8n-nodes-base.aggregate - OpenAI
@n8n/n8n-nodes-langchain.openAi - Gmail
n8n-nodes-base.gmail
From the author
Who is this for? This workflow is perfect for content creators, newsletter publishers, digital marketers, and virtual assistants who need a quick way to generate professional newsletters from trending news without manually curating and formatting articles.…