Deep research assistant with Perplexity AI and Telegram citations
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 8 nodes and runs on Telegram events (message). Along the way it connects OpenAI Chat Model, Perplexity and Telegram.
How it runs
Trigger: On Telegram events (message).
- Filter: keeps only the items that match a condition
- AI Agent: runs an AI agent, with model: OpenAI Chat Model; 2 tools (Perplexity Sonar, Perplexity Sonar Pro); memory: Window Buffer Memory
- 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 AI Agent (v1.7): 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 (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (7)
- AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Perplexity Tool
n8n-nodes-base.perplexityTool - Telegram Trigger
n8n-nodes-base.telegramTrigger - Telegram
n8n-nodes-base.telegram - Filter
n8n-nodes-base.filter
From the author
Turn your Telegram bot into a real-time research assistant with this intelligent n8n workflow. Designed for founders, analysts, and knowledge workers, this automation uses Perplexity Sonar and Sonar Pro to deliver concise, citation-rich answers to complex…