summree
The Easiest Way to Build an AI Agent (Zero Coding)
OpenAI
Chris Koerner on The Koerner Office Podcast

The Easiest Way to Build an AI Agent (Zero Coding)

⏱ 10 min video · 3 min read28 May 2026
TL;DR
Chris Koerner walks through building a no-code AI trend-monitoring agent using OpenClaw (self-hosted AI assistant) installed on a Hostinger server, controlled via Telegram. The agent browses the web 24/7 to surface trending business ideas and content angles, giving creators and entrepreneurs a first-mover advantage.
Key points
1
The stack is two tools: OpenClaw (self-hosted AI assistant) + Hostinger (managed server), costing less than a Mac Mini setup and requiring zero coding.
2
The agent runs 24/7 on Hostinger's server, so it keeps working even when your laptop is closed — no local hardware required.
3
You control the agent through Telegram (phone or desktop) or directly through the Hostinger dashboard; inputs and outputs sync across both simultaneously.
4
Web browsing is enabled via free ClawHub web_search and web_fetch skills; Claude (Anthropic) is used as the AI model, with Opus 4.7 recommended over the default Haiku.
5
To make it truly autonomous, Koerner recommends integrating with Zapier, Gmail, or Twilio so the agent proactively alerts you when relevant stories drop — rather than waiting for you to ask.
Actionable insights
Go to hostinger.com/kerneropenclaw, choose Managed OpenClaw, add web search (free), and use promo code KORNER OFFICE for 10% off — setup takes under 10 minutes.
In Telegram, create a bot via BotFather, paste the token into Hostinger, and approve the pairing code — this is the interface you use to talk to your agent on mobile.
Install the ClawHub web_search and web_fetch skills, disable browser automation, and switch the model from Haiku to Claude Opus 4.7 for faster, higher-quality results.
Write a system prompt that defines the agent's role (e.g. trend researcher for home service business ideas) and ask ChatGPT to help craft the prompt if you are unsure how.
Level up the agent by uploading your own content transcripts to train it on your voice, then connect it to Zapier or Twilio so it texts or calls you when a relevant story breaks.
Notable quotes

You are never going to be faster than an AI agent.

As it stands, this is really cool, but it is not much better than a Google search. So to level this up a notch, I would integrate it with some other tools like Zapier or my inbox, my Gmail, or Twilio.

Worth watching?
⏭️
Worth watching the full video?
The written summary captures every step of the build process clearly — only watch if you want to follow along with the screen recording as a visual guide while setting it up yourself.
Topics
AI & TechOpenAI

Explore more summaries on these topics →

Saved you some time? The creator still deserves a like.

Watch on YouTube →
More like this
Ghost AI let's AI Agents build disposable worlds
Wes Roth
Ghost AI let's AI Agents build disposable worlds
Wes Roth demonstrates why AI agents need isolated, disposable database copies (not just isolated code) when running parallel experiments. He uses Ghost, a Postgres service built around MCP and CLI, to show how forking databases per agent prevents one rogue agent from corrupting shared data — a lesson learned the hard way when an agent silently poisoned his LLM benchmark results.
2 min · 30 May 2026
EMERGENCY DEBATE: They Are Lying To Us About AI, The Iran War & What Happens Next!
The Diary Of A CEO
EMERGENCY DEBATE: They Are Lying To Us About AI, The Iran War & What Happens Next!
A three-way debate between Kevin O'Leary (pro-AI optimist), Cenk Uygur (unemployment doomer), and host Steven Bartlett on whether AI will cause mass unemployment, whether Chinese actors are sabotaging US data center development, and what the political fallout will look like heading into 2028. The conversation is heated, substantive, and covers real policy gaps nobody is addressing.
4 min · 28 May 2026
OpenAI just SOLVED MATH....
Wes Roth
OpenAI just SOLVED MATH....
An unreleased OpenAI general-purpose reasoning model has disproved a decades-old conjecture in discrete geometry (the Erdos planar unit distance problem), becoming the first AI to produce a genuinely publishable result on a prominent open math problem. Nine leading mathematicians, including Harvard's Melanie Matchett Wood, verified and endorsed the proof. The breakthrough came from the AI bridging two separate mathematical disciplines — algebraic number theory and discrete geometry — that human specialists had never connected for this problem.
3 min · 23 May 2026

Want this for your own channels?

Add the channels you follow. Every new video summarised and in your inbox the moment it drops. From £4/month.

Try it free