Course
Building AI agents that actually work
Six agents, built three ways — the concept, the no-code version, and the code. Written from the ones I run inside my own business, including the parts that break.
The problem
Most agent advice stops at the demo
The demo always works. You give it a goal, it thinks out loud, it produces something impressive. Then you point it at your actual work and it wanders, invents a number, or stops halfway and calls it done.
That gap is not a model problem. It is a missing done-condition, too many tools, and instructions written like a prompt instead of a job description. This course is about closing that gap, six times, on jobs a one-person business actually has.
Three tracks
Pick your depth, or read all three
Track A — Concept
What an agent is, the four parts, the stopping rule, and how to tell when a prompt or an automation is the better answer.
Track B — No-code
Every one of the six agents built in a no-code assistant builder: instructions, tools, done-conditions, and the failures to expect.
Track C — Code
The same agents in TypeScript: tool calling, loop control, structured output, step caps, logging and cost control.
The builds
Six agents
- Research agent — turns an open question into a decision brief with prices, trade-offs and sources.
- Triage agent — classifies incoming messages and drafts the obvious replies without ever sending.
- Content line — idea to outline to draft to edit, each step with its own standard so it keeps your voice.
- Extraction agent — mixed documents in, one clean spreadsheet row out, with a count check so nothing is skipped.
- Follow-up agent — finds the follow-ups that quietly never happen and writes the specific message for each.
- Operator agent — the multi-step one: several tools, chosen order, structured result, capped and logged.
What you get
Inside
- Six agent builds, each covered at all three depths.
- The instruction blocks I use, in full, ready to paste.
- A done-condition worksheet so every agent you build is checkable.
- The failure catalogue: what breaks in week two and the fix for each.
- Working code for the operator agent, including tool definitions and step limits.
- A cost-control section: where the money actually goes in an agent loop.
What you’ll learn
Module-by-module outcomes and time
Each module is designed to be completed in one sitting. Follow the no-code track straight through and you will have a working agent before the first hour ends.
Module 00
Boot sequence — what an agent actually is
- Define the four parts of an agent: goal, tools, loop, done-condition.
- Tell the difference between an agent, an automation, and a long prompt.
- Know when not to build an agent at all.
Module 01
Research agent — open question to decision brief
- Build an agent that searches, prices, and compares options without inventing facts.
- Set a stopping rule so it finishes instead of researching forever.
- Get the same agent in no-code and working TypeScript.
Module 02
Triage agent — classify and draft replies
- Route incoming messages by intent and urgency.
- Draft replies that never send without your eyes on them.
- Handle the ‘ambiguous’ case instead of guessing.
Module 03
Content line — idea to edited draft
- Split content work into idea → outline → draft → edit, each with its own standard.
- Keep your voice by giving the agent examples, not adjectives.
- Build a reusable content pipeline you can run weekly.
Module 04
Extraction agent — messy documents to clean rows
- Extract structured fields from PDFs, emails, and notes.
- Add a count check so skipped items surface immediately.
- Wire the output to a spreadsheet or CRM.
Module 05
Follow-up agent — find what quietly never happens
- Identify stalled conversations and missed commitments.
- Write the specific follow-up for each situation.
- Keep a human approval gate on anything that sends.
Module 06
Operator agent — several tools, one result
- Sequence multiple tools in the right order.
- Use structured output and step caps to stay predictable.
- Log every decision so you can debug the loop.
Module 07
Deployment, cost control, and the failure catalogue
- Estimate real cost per run before turning an agent loose.
- Recognize the five most common week-two failures and their fixes.
- Leave with a done-condition worksheet for every future agent.
Total course time
About 5 hours 10 minutes if you complete every module at every depth.
First working agent
Roughly 30 minutes if you run Module 00 straight into Module 01’s no-code track.
Best for
Solo operators and small teams who want two or three agents running on real work — not a tour of every framework.
Not for
Anyone looking for an autonomous business. Everything here keeps a human on anything that sends, spends or deletes.
Straight answer
I am one person building this business in public. This course teaches the agent setups I run here, with their limits stated. It will not make you money on its own and I make no earnings claims — it will get working agents into your week.
Read first
Three lessons, free and complete
How to buy and access the course
Everything that happens before and right after checkout, in plain language.
1. How to buy
- 1
Choose your purchase
Click the buy button on this page. The course is $19, one payment, no subscription.
- 2
Pay securely
Stripe opens right here on the page. You can pay with card, Apple Pay, Google Pay, or Link. I never see or store your card details.
- 3
Confirm instantly
Payment usually confirms within a few seconds. You will see a confirmation page with your download link immediately.
2. Access after checkout
Download email arrives
A secure download link is sent to the email you used at checkout. It is valid for 30 days and can be used multiple times.
Get your files
The email links to the 155-page course PDF and the working code bundle ZIP. Click once, download both.
Permanent library copy
If you create an account or already have one, the course is also saved to your library at /library forever.
Onboarding email timeline
After purchase you will get a short sequence of emails that walk you from "I bought a PDF" to "I have one agent running." You can unsubscribe from non-transactional emails anytime.
Troubleshooting
Questions
Before you buy
- Do I need to be able to code?
- No. Tracks A and B require none. Track C is there for when you outgrow the no-code version, and it is written so you can read it before you can write it.
- Which tools does it lock me into?
- None. The no-code track is written against the three things any assistant builder must have — persistent instructions, tools, and a destination — so it survives you switching platforms.
- Is this theory or builds?
- Builds. Every section ends with something running. The concept track exists because skipping it is why most people's first agent does not work.
- Can I see some of it first?
- Yes. Three lessons are published free and in full: what an agent is, one complete no-code build, and the six patterns. They are linked below.
- What exactly do I get, and how?
- A 155-page PDF course plus the working code bundle as a ZIP. After payment you get an emailed secure download link and, if you have an account, a permanent copy in your library.
- How long does delivery take?
- Immediately. The download link is issued the moment payment confirms — usually within a few seconds. If the email is slow, the same files are on the confirmation page.
- Is it one payment or a subscription?
- One payment of $19. No renewal, no upsell required to use what you bought, and updates to the course are included at no extra cost.
- How long does it take to work through?
- About 30 minutes to your first working agent if you follow the no-code track straight through. The full six builds take a few evenings, and it is written to be used one build at a time.
- Do I need paid AI accounts to follow along?
- You need access to one assistant that supports custom instructions and tools. The no-code track works on the common consumer tiers; the code track uses standard API calls and the costs section shows where spend actually goes.
- What is the refund policy?
- 14 days. If it is not what I described, email me and you get your money back — no argument, and you keep nothing you have to return.