Who is this course for?

People who want an agent that can read, decide, and take the next step, with a person still in the loop where a mistake would hurt.

Do I need to be a developer?

You need to be willing to connect tools and read what the agent did. You do not need a computer-science degree.

How is this different from Build Your First AI Agent?

The first-agent course hands one repeated task to an agent. This course is the agent that can act across steps, and the stop you put in front of it.

What do I leave with?

One agent you built, the recordings, and a certificate of completion. The tool accounts are yours.

Do you guarantee a job after a cohort?

No. We publish dates, prices, refund terms and consented stories. Placement and income claims are not part of this academy.

What time zone are live sessions in?

Source zone is America/Toronto unless a cohort says otherwise. Session times always name that zone. Convert in your own calendar from the ICS on the cohort card.

Can I join a waitlist if a cohort is full?

Yes. Waitlist captures name, email and optional phone. It does not take payment. Seats that free up are offered in join order.

How does early-bird pricing work?

If a cohort has an early-bird price and the cut-off has not passed (server date at payment), checkout charges the early-bird amount. The cart may still show list price until quote.

What is the refund window?

Full refund before the published cut-off relative to the cohort start; after that the published bands on the Refund page apply. Checkout requires you to accept that policy.

AI (legacy tools) · NGS-1026

Build Autonomous AI Agents

A chatbot answers. An agent goes and does the next step. In two live weeks you build one that can read, decide, and act, and you keep a person in the loop where a mistake would hurt. You leave with an agent that runs, not a diagram of one.

12 hours
Practitioner
Live virtual
December 5 — December 13

Benefits

A working agent for a job you already do.
A one-page guardrail: what it may do, and where a person says yes.
A short case with the time saved, and the claim you will not make.
Recordings of the two weeks.
A certificate when you finish.

Course overview

12hours

1
From chat to action
2
Prompts that hold
3
Build it without code
4
Memory and your own documents
5
Tools and actions
6
More than one agent

This is a hands-on course for analysts, managers, product owners, and IT people who do not write software for a living. No programming is required. You start from the difference between a chat and an agent, then you build. You will give an agent a job, a way to remember, and tools it may use. You will see when one agent is enough and when a small team of agents is the honest design. You will put a checkpoint where the decision is risky, and you will write down how you will know the agent is worth the money. The class uses no-code studios. You do not need a paid seat before you arrive. Prompt and Context Engineering is useful, not required. Build Your First AI Agent is the shorter course, for one repeated task. This one is for an agent that plans, uses tools, and can work with another agent. Dates and the fee are on this page.

Outcomes

What you will be able to do when the course ends. This is not the list of things you take home. That list is Benefits, at the top of the page.

1You can tell a chatbot from an agent that is allowed to act.
2You can build a first agent in a no-code studio.
3You can say what it may read, what it may remember, and what it must forget.
4You can name the tools it may use, and the step that still needs a person.
5You can put two agents on one job without losing who decides.
6You can show whether the agent saved time, or only made a demo.

Curriculum

Every chapter is listed here. You enrol in the whole course, not one chapter.

Module 1
From chat to action
What an agent is, the loop it runs, and how much you let it decide.
- A chat answers. An agent acts.One replies. The other takes a next step. You will not mix them up again.
- The loopSee, reason, plan, act. Then look at what happened.
- Reason, then actA pattern for thinking a step out loud before the tool is used.
- How much freedomA person checks every step, or the agent runs. You pick the point on that line.
Module 2
Prompts that hold
A prompt that survives a real task, and an output the next step can use.
- More than one exampleShow the agent the shape of a good answer, not only the task.
- A role, and a checkWho it is, and a second pass that looks for the mistake.
- An output the next step can readA list or a table, not a paragraph the next tool cannot use.
Module 3
Build it without code
From a requirement to a working agent in a no-code studio.
- The studiosA no-code place to build. You do not need to write a program.
- From a requirement to a screenThe job, the user, and a first version you can click the same day.
Module 4
Memory and your own documents
What the agent may read, and what it must forget.
- Reading your own filesThe agent answers from your documents, not from a guess.
- This session, and the next oneWhat it may remember for an hour, and what it may keep.
Module 5
Tools and actions
When the agent may call a system, and when it must stop.
- Giving the agent a toolA search, a table, a system. Name what it may touch.
- When it may act aloneThe rule for a safe action, and the rule for one that waits.
Module 6
More than one agent
A small team of agents, and who is in charge.
- A small teamOne looks. One writes. You say who speaks first.
- Who is in chargeIf two agents disagree, a person or a rule decides.
Module 7
When it goes wrong
A picture of the flow, and a path for the answer you did not expect.
- Draw the flowThe states, and the line back when the answer is not good enough.
- A fallbackWhat the agent does when the instruction is unclear. Silence is not a plan.
Module 8
Guardrails
Privacy, bias, and the decision a person still makes.
- What it must not doBias, private data, and a decision that needs a person.
- A checkpoint you can point atThe step where a human says yes before the action leaves the building.
Module 9
Was it worth it
The numbers, the business case, and your capstone.
- The numbersTime, errors, and what one task costs before and after.
- The case for itWho benefits, what you will not claim, and when you would turn it off.
- Capstone: an agent that watchesIt reads a market signal, drafts a brief, and stops for a person before anyone acts on it.

Schedules for Build Autonomous AI Agents

AGT-2026-12