Guides
All analyses › Стас Быков
You’re on YouTube for AI entrepreneurs. Read the analysis and decide whether the video is worth your time.All analyses →
AI Automation via Agents from Scratch: New AI Agents in n8n (Review)
Author’s title: AI Automation via Agents from Scratch: New AI Agents in n8n (Review)

Actually: Build autonomous agents that research RSS and post to Telegram; setup takes about 5 minutes.

С
Стас БыковIT, AI and SEO for business in plain words · 9K views · 16 days ago
7/10
BUSINESS SCORE
🛠 Tools overview
Practicality8
Specifics7
Novelty8
▶ Worth watching. Watch for the specific node configurations and tool logic. This is a must-watch for business owners using n8n who want to move beyond rigid workflows to autonomous AI agents that can decide which tools to use for complex tasks. · video 14:42

🔎 What’s inside

The video demonstrates how to set up and use the new 'Agents' feature in n8n to build autonomous assistants. It shows a practical example of a content agent that researches news via RSS, writes posts, and manages a Telegram channel by selecting the right 'tools' (workflows) on its own.
Promise vs. reality
The title is accurate; the video provides a comprehensive guide to setting up n8n's new AI Agent functionality and demonstrates its practical application for business automation.

⚡ The gist in 30 seconds

  • n8n's new AI Agents feature allows creating autonomous assistants that can select and execute specific workflows (tools) based on natural language instructions.
  • Unlike rigid linear workflows, agents can handle multi-step tasks like researching a topic via RSS, saving drafts to a database, and requesting human approval before posting.
  • The system supports the Model Context Protocol (MCP), allowing external AI models to interact directly with n8n agents and their tools.
  • Business owners can automate content marketing by setting schedules for agents to find news, rewrite it in a brand voice, and publish it across channels.
👤 Stas Bykov, a technology expert and automation specialist.

⏱ Key moments click — the video jumps there

Introduction to the new AI Agents feature in n8n and how it differs from standard workflows.
Step-by-step guide to creating an agent, selecting AI models like GPT-5.6 Terra, and setting instructions.
Defining 'Tools' for the agent by connecting existing n8n workflows for saving drafts, reading data, and sending messages.
Enabling MCP (Model Context Protocol) to allow external AI models to access the n8n agent's capabilities.
Live demonstration of the agent generating a business post from a voice prompt and saving it to a database.
Setting up an automated schedule (Cron) for the agent to operate independently without manual triggers.
Integrating RSS feeds as a tool for the agent to fetch and process real-time industry news.
Comparison of AI Agents vs. traditional linear workflows: why agents are better for complex, non-linear tasks.

💰 Numbers

n8n setup time5 minutes (author's claim)
Free trial for SpaceWeb VPS3 days (author's claim)
Post length constraint500-1100 characters (shown on screen)
Scheduling frequencyEvery minute for testing (shown on screen)
Numbers are quoted from the video authors.

🛠 Tools from the video

n8n — low-code workflow automation platformOpenAI GPT-5.6 Terra — AI model used for the agent's logicSpaceWeb — VPS hosting provider for running n8nTelegram — messaging platform for content deliveryRSS — protocol for fetching news updates

🚀 How to apply it in your business

  1. Create an n8n agent and provide it with a 'Knowledge' base of your company's brand guidelines.
  2. Connect a 'Save Draft' workflow to a database to store AI-generated content for review.
  3. Set up a 'Send Telegram' tool that the agent can call only after a specific confirmation keyword.
  4. Use an RSS feed node to feed industry news to the agent for automated daily summaries.
  5. Configure a schedule (Cron) to trigger the agent at specific times for autonomous operations.

Who will this analysis save an hour?We’ll send the link with the “actually” takeaway — they won’t have to watch the whole video.

🎯 Who it’s for

Content Managers looking to automate multi-channel postingBusiness Owners wanting to build custom AI assistants for internal tasksAutomation Specialists transitioning from linear bots to autonomous agents
⚠️ Watch out: The video uses model names like 'GPT-5.6 Terra' which appear to be custom-named or future-dated in the demo environment; ensure your API provider supports the specific models you intend to use.

❓ Questions and answers

How to create an AI agent in n8n?

To create an agent, go to the 'Agents' tab in n8n and click 'Create Agent'. You need to select a model (like GPT-4 or 5.6), provide detailed natural language instructions, and attach 'Tools' which are essentially other n8n workflows that the agent can trigger.

What is the difference between an n8n agent and a workflow?

A standard workflow follows a rigid, step-by-step path defined by the user. An AI agent is autonomous; it looks at the available tools (workflows) and decides which one to use and in what order based on the user's prompt.

Can n8n agents post to Telegram automatically?

Yes, you can create a specific workflow for sending messages to Telegram and attach it as a tool to your agent. The agent can then be scheduled to find information, write a post, and use that tool to publish it.

How to use RSS feeds with AI agents?

You can create a workflow that reads an RSS feed and returns the latest articles. By adding this workflow as a tool to your agent, the agent can 'read' the news whenever it needs fresh data for content creation.

What is MCP in n8n?

MCP stands for Model Context Protocol. In n8n, it allows external AI interfaces (like ChatGPT) to 'see' and interact with your n8n agents and their tools, effectively bridging your local automations with global AI models.

Found a mistake in the analysis? Tell us what’s wrong and we’ll fix it.
Want analyses like this for your niche? We’ll send the best videos for your business.