Step 1: Setting Up Your Make Account – Your Automation Hub
First things first, if you haven’t already, you’ll need to sign up for a Make account. Head over to their website (www.make.com) and create an account. They usually have a free tier that’s perfect for getting started and experimenting with automation. Once you’re signed up and logged in, you’ll be in your Make dashboard. This is where you’ll build your automation workflows, which they call “scenarios.”
Step 2: Creating a New Scenario – Your Automation Blueprint
In your Make dashboard, look for a button that says something like “Create a new scenario” or just a big plus (+) icon. Click on that. This will take you to the scenario builder, which is a visual canvas where you’ll connect different apps and define how data flows between them.
Step 3: Adding Your First Module – The ChatGPT Magic
The first thing we need in our scenario is the ChatGPT module. In the scenario builder, you’ll see a big circle with a plus (+) sign in the middle. Click on that. A window will pop up asking you to “Choose a module.” In the search bar, type “OpenAI” (that’s the company behind ChatGPT). Select the “OpenAI” module.
Once you’ve selected OpenAI, you’ll see a list of actions you can perform. For our purpose, you’ll likely want to choose an action like “Create a completion” or “Chat – Create a completion.” This is the module that will actually send your prompts to ChatGPT and get the generated text back.
Step 4: Connecting Your OpenAI Account – Giving Make Access
Now, Make needs permission to talk to your OpenAI account. After selecting the ChatGPT action, you’ll probably be prompted to “Add new connection” or select an existing one. Click on “Add new connection.” A window will pop up asking for your OpenAI API key.
To get your OpenAI API key, you’ll need to head over to the OpenAI platform (platform.openai.com), log in, and go to the “API keys” section (usually under your profile). Click on “Create new secret key.” Give it a name if you want, and then copy the generated key. Be careful to store this key securely, as it gives access to your OpenAI account.
Back in Make, paste your OpenAI API key into the required field and click “Save.” Now, your Make account is connected to your OpenAI account.
Step 5: Configuring the ChatGPT Module – Telling It What to Write
This is where the real fun begins! You need to tell ChatGPT what kind of blog post you want it to write. In the ChatGPT module settings, you’ll see various fields you can configure. Here are some important ones:
- Model: Choose the ChatGPT model you want to use.
gpt-3.5-turbois usually a good balance of speed and quality, but you might want to experiment with others likegpt-4for potentially better results (though it might be more expensive). - Prompt: This is the most crucial part! Here, you’ll write the instructions for ChatGPT. Be as clear and specific as possible about the topic, desired tone, length, target audience, and any specific points you want it to cover. For example, you could use a prompt like: “Write a blog post about the top 5 benefits of using automation in content creation. The tone should be informative and slightly enthusiastic, aimed at bloggers who are new to automation. The post should be around 500 words.” You can get really creative here!
- Max tokens: This setting controls the maximum length of the text ChatGPT will generate. One token is roughly equivalent to 3-4 characters or about ¾ of a word. For a blog post around 500 words, you might set this to around 700-800 tokens to be safe.
- Temperature: This setting controls the randomness of the output. A lower value (e.g., 0.2) will make the output more focused and deterministic, while a higher value (e.g., 0.8) will make it more creative and unpredictable. Experiment to see what works best for your needs.
You can also configure other parameters like n (number of responses to generate) and stop (sequences where the API should stop generating further tokens).
Step 6: Adding the Next Module – Where Your Blog Lives (WordPress!)
Now that you have ChatGPT generating your blog post, you need to tell Make where to put it – which is likely your WordPress website. Click the “Add another module” button (the plus (+) sign next to the ChatGPT module). In the search bar, type “WordPress” and select the WordPress module.
You’ll see a list of actions you can perform with WordPress. For creating a new blog post, you’ll probably want to choose an action like “Create a post.”
Step 7: Connecting Your WordPress Account – Giving Make the Keys to Your Blog
Just like with OpenAI, Make needs permission to access your WordPress site. After selecting the “Create a post” action, you’ll be prompted to “Add new connection” or select an existing one. Click on “Add new connection.”
A window will pop up asking for your WordPress URL, username, and password (or an application password if you have that set up for security). Enter these details carefully and click “Save.” Make will then establish a connection with your WordPress site.
Step 8: Configuring the WordPress Module – Mapping the ChatGPT Output
Now, you need to tell the WordPress module where to get the blog post content from the ChatGPT module. In the WordPress “Create a post” module settings, you’ll see fields like “Title,” “Content,” “Status,” etc.
For the “Title” field, you might want to have ChatGPT generate a title as well. So, in your ChatGPT prompt, include instructions like “Also generate a catchy title for this blog post.” Then, in the WordPress “Title” field, you can use Make’s mapping feature to select the part of the ChatGPT output that contains the title. This usually involves clicking in the “Title” field and then selecting the relevant data item from the ChatGPT module’s output (it might be something like {{1.choices.0.message.content}} and you’ll need to figure out which part holds the title based on ChatGPT’s response structure).
Similarly, for the “Content” field in WordPress, you’ll map it to the part of the ChatGPT output that contains the main body of the blog post.
You can also configure other WordPress post settings like the post status (e.g., “Draft” or “Publish”), author, categories, tags, etc. You might even want to add more ChatGPT prompts to generate these as well and map them accordingly in Make.
Step 9: Testing Your Scenario – Making Sure Everything Works
Once you’ve configured both the ChatGPT and WordPress modules, it’s time to test your scenario. At the bottom of the Make scenario builder, you’ll find a “Run once” button. Click on that.
Make will then execute your scenario. It will send your prompt to ChatGPT, and if everything is set up correctly, ChatGPT will generate a response. Then, Make will take that response and attempt to create a new post on your WordPress site.
Check your WordPress dashboard to see if the new post has been created with the title and content you expected. If there are any errors, Make will usually show you where the problem occurred, and you can go back and adjust your module settings.
Step 10: Scheduling Your Scenario – Automating the Automation!
Once you’re happy with how your scenario is working, you can set up a schedule to run it automatically. At the bottom of the Make scenario builder, you’ll see a “Scheduling” option. You can set it to run at specific times (e.g., once a day, once a week) or based on other triggers if you have a more complex workflow in mind.
And that’s the gist of it! You’ve now set up an automation in Make that uses ChatGPT to generate blog posts and automatically creates them on your WordPress site. Remember to experiment with different prompts and settings to get the best results. You can also add more modules to your scenario to further automate your workflow, like automatically sharing your new blog post on social media. The possibilities are pretty endless!
