Gmail to Telegram: email summaries with OpenAI GPT-4o
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 6 nodes and runs on Gmail events. Along the way it connects Gmail, OpenAI Chat Model and Telegram.
How it runs
Trigger: On Gmail events.
- Set summary language (Edit Fields (Set)): sets 1 field: summary_language
- Prepare fields for agent (Edit Fields (Set)): sets 4 fields: summary_language, from, subject…
- Summary generation agent (AI Agent): runs an AI agent, with model: OpenAI Model
- Send summary to Telegram (Telegram): uses Telegram
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 Summary generation 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.
- Also check Gmail Trigger below v1.4 runs as v1.4 (drafts skipped, max emails per poll).
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) Summary generation 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 (5)
- Edit Fields (Set)
n8n-nodes-base.set - Gmail Trigger
n8n-nodes-base.gmailTrigger - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Telegram
n8n-nodes-base.telegram - AI Agent
@n8n/n8n-nodes-langchain.agent
From the author
🧑💼 Who is this for? This workflow is for anyone who receives too many emails and wants to stay informed without drowning in their inbox. If you're constantly checking your Gmail and wish you had someone summarizing messages and sending just the important…