Course contentModule 1 · Lesson 1
What automation takes off your plate, and what it does not
You learn which of your tasks are actually worth automating, and make that call with a simple three-question framework.
MODULE 1 / WHAT THIS IS ABOUT
Sort first, build later
Before you build anything, it's worth taking a quiet half hour to sort things out. Which of your tasks are good candidates for automation, and which aren't? That's what this lesson is for. It doesn't promise that a machine will take over your work. It gives you a simple framework to judge for yourself what's worth the effort and what you're better off doing by hand. If you walk away with an honest list instead of a vague hope, this lesson has done its job.
I put this first on purpose, because most lost time isn't lost while building. It's lost before that, by choosing the wrong task to automate. That's what we want to spare you.
What a workflow is, in an everyday picture
First, the key term: a workflow is a chain of automatic steps that run one after another as soon as something specific happens. That's all there is to it.
Picture your desk. A new inquiry comes in by email. You read it, add the name to your contacts, create a note, and send a short acknowledgment back. Four small steps, the same every time, always in the same order. That's the chain a workflow handles for you. It waits for the trigger (the new email), then works through the steps without you sitting there watching.
A workflow is reliable because it's stubborn. It does exactly the same thing every time, without getting tired or skipping a step, even the hundredth time on a Friday afternoon. The tradeoff is that it can't do anything it wasn't given as a rule upfront. It's a diligent, conscientious colleague with no judgment of its own.
Remember
A workflow is an assembly line for busywork. Each station does exactly one thing and passes the result along. All you decide at the end is whether it goes out.
Where the workflow stops: judgment
And that brings us to the boundary that holds this whole course together. A workflow reliably handles what can be captured in rules. But it can't replace judgment, meaning the ability to read a situation that has never come up quite like this before.
Back to the desk. Sending an acknowledgment is pure rule-following. The workflow can do that. But do you take on this project at all, and at what price? What tone do you take with a frustrated client? Does this one inquiry seem risky? That's judgment. It depends on context only you have, and on a decision only you can and should make.
That's why the promise of this course isn't "sit back, the AI will handle everything." It's this: automation takes the recurring grind off your hands and puts the result in front of you for approval. The final call stays with you.
Note: The thread running through this course
You're not building a machine that acts on its own. You're building a diligent assistant. It gathers, sorts, and drafts, then puts the result in front of you: "Here's my suggestion. Want to take a look?" You say yes or make changes. That approval step isn't a flaw to be optimized away later. It's the whole point, and your safety net.
The framework: three questions for any task
Now the practical tool. Whenever you have a specific task in front of you and want to know whether it can be automated, run it through three questions. Grab a real task from your week right now and try it out.
First: is it recurring? Do you do this often, in roughly the same form, not just once? Something you do once a year rarely justifies the setup. The acknowledgment you send three times a day is worth it.
Second: can it be captured in rules? Does the same kind of input come in each time, and is there a consistent, sensible response? "New inquiry comes in, so acknowledgment goes out" can be captured in rules. "Depends on who wrote and how I'm feeling right now" can't.
Third, and this is the key question: does the final decision stay with you? A task is only a good candidate when you can picture the machine preparing something and you approving it. If the thought of it going out unchecked makes you uncomfortable, that isn't a reason to avoid automation. It's a signal that an approval step belongs in the workflow.
A task that gets three yeses is a strong candidate. If the first or second yes is missing, do it by hand. The third question is never about yes or no, only about where in the workflow you step in to approve.
Check one of your own tasks
Here's a self-check to copy so you can try this with your own work. Take a task that annoyed you this week, describe it in one sentence, and have it evaluated against this framework. Paste it into the AI tool you use.
I am checking whether a recurring task of mine is worth automating.
Here is the task in one sentence:
[Describe your task, for example: "After every new inquiry I add the
contact and send a short acknowledgement."]
Ask me these three questions one at a time, wait for my answer each
time, and then summarize at the end:
1. Is this task recurring, meaning do I do it often in a similar form?
2. Can it be ruled, meaning does the same kind of input come in each
time and is there a consistent sensible response?
3. Where do I want to check and approve before a result goes out?
Summarize in two or three sentences at the end: is this a good
candidate for automating? And if yes, where should the approval step
go? Speak plainly, no technical language.
Try this with two or three tasks. You'll quickly develop a feel for which ones are worth it and which ones you're better off keeping. That's the feel this lesson is meant to give you.
You end up with a list
This lesson doesn't build anything. When it's over, no workflow is running and you haven't set up any software. That's exactly right. It helps you sort out your expectations. And it gives you a list: a few tasks worth automating and a few you're choosing to keep doing by hand. That's the foundation everything else rests on.
What the framework can't do: it doesn't decide for you, and it doesn't replace a look at data and privacy rules. As soon as a task involves other people's personal data, there's an extra check to do before you build anything. We'll cover that later, where it belongs in the course. We won't skip it.
Knowledge Check
If you have a task in mind that got three yeses, the next question is: what tool do you use to build it? In the next lesson, we look at which kind of tool fits which kind of task. We also look at why you start your first workflow deliberately small.