How I Build 27 AI Agents Without Writing Code
25 Aug 2026
Twenty-seven AI agents work for me. I have never programmed.
Twenty-seven AI agents work for me. I have never programmed.
A new edition of my LinkedIn newsletter is out, and it answers the question I get more than any other: how do you actually build these things?
The industry answer involves courses, frameworks and budgets. Mine fits in one sentence.
What is inside:
→ What my agents are really made of (text files, in plain English)
→ The five parts of every agent file (shown on a real one from my laptop)
→ Two rules before you start (one decides where it stops and asks you)
One problem, one afternoon. That is the entry ticket.
Which problem would you describe first?
What this means for leaders who think AI is someone else's job
Most of the leaders I coach did not grow up writing code, and they assume that rules them out of building anything real with AI. It does not. The skill that matters now is the one they already have: knowing exactly what a good outcome looks like, and being able to explain it clearly to someone new.
That is precisely what an agent file is: a clear brief, written once and reused every day. The people who get the most out of AI right now are rarely the most technical people in the room. More often they are the ones willing to sit down and write out, step by step, how they actually want a task done, which is closer to management than to engineering.
I see this pattern constantly in the workshops I run. The leaders who move fastest are the ones who stop waiting to feel technical enough, pick one recurring task, a status update, an inbox they dread, and write down exactly how they would explain it to a new hire.
If this resonates and you want a practical guide, I have a free AI Tools & Tips Guide that walks through the AI tools I actually use as a coach and business owner, and how I use them. Leave your email here and I will send it over: https://www.thechangerepublic.com/free-resources