Level: Assist. You are working alongside the AI. You write the ask, you check the answer, and you decide what ships. Nothing goes out in your name without your review.

What this course is

Most people who try an AI assistant and walk away disappointed did not use a bad tool. They used a vague ask. The gap between a generic answer and a usable one is almost always the quality of the request and the quality of the review that follows it.

H.E.L.P. is the method Nantucket AI teaches for closing that gap. Four steps, in order, every time:

• Humanize. Give the AI context, role, audience, and voice so the output

sounds like you and fits your situation.

• Evaluate. Judge the output against your own knowledge. Check facts,

identify gaps, decide what needs to change, then ask for more.

• Leverage. Put the output to work in your business and connect it to the

next task.

• Perfect. Refine wording, format, and fit until the work is genuinely

yours, and build reusable prompts from what worked.

The method is deliberately plain. You already do a version of it every time you brief a new hire. You tell them the situation, you look at their first draft, you use what is good, and you tell them what to fix. H.E.L.P. is that same habit applied to a tool that will otherwise guess.

Who it is for

Nantucket business owners, executive directors, board members, managers, and their teams. No technical background is required. If you can type a question into a chat box, you can complete this course.

What you will be able to do

By the end you will be able to:

1. Explain why the quality of the ask determines the quality of the output.
2. Write a prompt that carries context, role, audience, and voice.
3. Review AI output against your own knowledge and catch what is wrong,

missing, or risky before it goes anywhere.

1. Turn one piece of AI output into several finished pieces of work.
2. Refine drafts to your standard and save the prompts that worked as reusable

templates for your team.

1. Apply the Human-In-Command rule so AI supports your people instead of

speaking for them.

Product neutrality

This course is deliberately tool-neutral. Everything here works in any chat assistant you already have access to. We say “your chat assistant” and mean whichever one you use. No product names, no pricing, no claims about what a specific vendor’s model can or cannot do. The method outlasts the tools.

How the course is assessed

Each module ends with a short quiz. Every question is answerable from that module’s lessons. A final assessment covers all five modules.

• Passing grade: 70 percent.
• Retakes: unlimited. Take a quiz as many times as you want. Retakes are not

penalized and do not affect your completion status.

Modules

#	Module	Lessons	Focus
1	Why You Need a Framework	4	The art of the ask, what lazy prompts cost you, Human-In-Command, and the four letters at a glance
2	Humanize	3	Context, role, audience, and voice
3	Evaluate	3	Judging output, checking facts, finding gaps, asking for more
4	Leverage	3	Putting output to work and chaining it to the next task
5	Perfect	3	Refining to your standard and building a reusable prompt library

Related

• Trust Ladder: /trust-ladder/
• The H.E.L.P. Method: /the-help-method/
• Related course: What Is an AI Agent (Orient level)

Frequently asked questions

Do I need to know anything technical to take this course?

No. If you can type a question into a chat box, you can complete this course. There is no code, no setup, and no math. The whole method is about writing down what you already know about your business.

Which AI tool do I need?

Whichever one you already have. This course does not teach a product. Every lesson and every exercise works in any chat assistant, and we deliberately avoid naming products because they change faster than the method does.

What is the difference between this and Course 1, What Is an AI Agent?

Course 1 is Orient level. It explains what these tools are, what they can and cannot do, and how to think about supervision. This course is Assist level. It is hands-on. You will write prompts, review real output, and finish with templates you use at work. Course 1 helps, but it is not required.

Is “Expand” still the E in H.E.L.P.?

No. The E is Evaluate. Earlier Nantucket AI material used Expand, and Evaluate now carries that meaning and more. Expanding a draft is the second half of the step. The judgment comes first. If you ask for more without judging what you already have, you get a longer draft with the same problems in it. This page is the framework’s current, authoritative definition.

What is the passing grade, and what happens if I fail a quiz?

Passing is 70 percent, and retakes are unlimited. Retakes are not penalized and do not affect your completion status. Quiz questions are answerable strictly from the lesson text, so a wrong answer usually means one section is worth rereading.

Can my whole team take this together?

Yes, and it works better that way. Module 4 covers running a staff workshop and building a shared prompt library, which is the practice that actually changes how a business operates. Individual accounts track progress separately.

Where this course sits

This is an Assist course, the second rung of the Nantucket AI trust ladder, and the home of the H.E.L.P. method this course teaches. Take What Is an AI Agent first if the word “agent” is still unfamiliar.