A guide to building AI workflows with Claude Code (even if you're not technically savvy)

Many people's writing process used to be quite messy. They would often start by letting out all the ideas swirling in their heads. Then, they would try to organize them into an outline. But people usually lost patience with that, so they would just start writing.

 

Then they realized they didn't know where they were going, so they stopped and went back to the outline. It was quite a laborious process, constantly going back and forth between writing and outlining.

But things are different now. When things get stuck, don't start writing right away; ask Claude for help.

 

Claude will review your outline and help you fill in the blanks. He often suggests things you haven't thought of. This is good because it helps you find the core of what you want to say. Instead of writing down your thoughts, discuss to find out what you need to say.

But Claude is more than just a tool for consultation. Use it to help you brainstorm headlines, explore different outline options, critique sections as you write, conduct supporting research, act as a thesaurus and glossary, offer SEO suggestions, and much more.

 

As a result, you will be able to write significantly more.

But don't design this workflow all at once. Do it step by step. It all starts when you ask yourself, "How can Claude be of help with this?".

In a previous article, TipsMake.com shared how to choose workflows to automate (or support) with AI . This time, we'll delve into how to design personalized workflows using AI. The article will use a specific person's writing process to illustrate the main steps. But you can also apply your own ideas.

You'll find that designing workflows using AI is very similar to designing product solutions. In fact, we'll rely on discovery habits to achieve that.

Create a flowchart of the steps needed to complete the task.

Once you've determined the AI ​​workflow you want to create, start by accurately mapping out the steps needed to complete the task yourself.

If you find this difficult, you may need to attempt the task a few more times and take notes as you go.

Here's what to do when writing a blog post:

1. Choose a topic.
2. Write down everything you can think of related to that topic.
3. Structure them into an outline.
4. Research to fill the gaps.
5. Write it in parts.
6. Edit each section individually.
7. Think about SEO strategies.
8. Come up with ideas for headlines.
9. Decide which images to add.
10. Submit your article to the editor for editing.

If this looks like story mapping, you're right. Instead of mapping out what the customer has to do to get value from your solution, you're mapping out what needs to be done to accomplish a task.

And it has similar benefits. It allows you to see exactly what needs to happen and gives you the opportunity to start asking, " Where can artificial intelligence help?"

From here, you will:

1. Choose a step to automate or assist with using AI.
2. Deciding on the right automation (or support) strategy: Code vs. LLM
3. Build the first workflow prototype with detailed instructions for each step.
4. Check and repeat the work procedures.

This article has provided sufficient guidance for you to follow and finish with your first draft of an AI workflow.

I hope you find this helpful!