Track real estate market pain points with Apify, GPT-4o and Telegram alerts
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 9 nodes and runs on a schedule (every day). Along the way it connects Airtable, Telegram and OpenAI Chat Model.
How it runs
Trigger: On a schedule (every day).
- Apify Scraper (HTTP Request): calls an HTTP API
- Extract Summary (Code): runs custom JavaScript code
- Extract Pain Points (AI Agent): runs an AI agent, with model: OpenAI Chat Model
- Store to Airtable (Airtable): create
- Compare Pain Points (Code): runs custom JavaScript code
- Telegram: uses Telegram
- Read Yesterday Pain Points (Airtable): uses Airtable
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 Extract Pain Points (v1): 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) Extract Pain Points (v1) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (7)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - AI Agent
@n8n/n8n-nodes-langchain.agent - Airtable
n8n-nodes-base.airtable - Telegram
n8n-nodes-base.telegram - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi
From the author
How it works This workflow runs on a daily schedule. It starts by scraping real estate-related queries from Google using Apify. The organic search results are parsed and summarized into a single text block. That text is then sent to an AI model (GPT-4o) which…