Prompt Playbook: AI Powered Atomic B2B Newsletter 3

Hey Prompt Entrepreneur,

I can already hear some of you saying, "Kyle, what have you done to me? I set up those Zapier feeds like you suggested, and now my spreadsheet is exploding with content. This is worse than before!"

First off—I apologise! I just opened up a firehose of information and pointed it straight at your Google Sheet. That wasn't very considerate, was it?

But hold on before you close this tab in frustration. The database we built yesterday isn't meant to be your final destination for content review. It's just a holding tank—a repository where everything gets collected before the real magic happens.

We've built the plumbing to bring water into the house, but we haven't installed the filters yet. That's what we're doing today - adding a crucial filtering layer that transforms an overwhelming flood of content into a manageable, curated stream of high-quality candidates for your newsletter.

Sounds good? Sorry we had to do set up the firehose first! But we need the holding tank first!

By the end of today's session, you'll have an AI system that reads everything for you, summarises it, rates its relevance, and presents you with only the most promising items. Your morning review will go from overwhelming to effortless.

Let's get started:

The Problem with Information Overload

Even with just 5-10 sources feeding into your content database, you could easily end up with 30-50 new items each day. Reading all of that would defeat the purpose of our efficient atomic newsletter system…

This is where AI becomes our essential ally. We're going to build a filtering layer that processes this information flood and distills it down to only the most relevant and valuable content for your specific newsletter.

First, let's make sure we're properly setting up new content with the correct status. In Let’s adjust the Zapier action that adds content to your Google Sheet (that we made in Part 2).

You need to explicitly map "New" to the Status column:

In the Google Sheets action of your Zapier workflow:

• When mapping fields, scroll down to the Status column

• Instead of mapping dynamic content, enter the static text "New"

• This ensures every new piece of content automatically gets marked as "New"

We’ll use this to trigger actions shortly.

Content Quality Criteria for AI Filtering

Before we dive into the technical setup, we need to clearly define what makes content worthy of inclusion in your newsletter. This will form the basis of our instructions to the AI.

And it depends on what type of newsletter you are building.

Remember the newsletter type you chose in Part 2? Your content criteria should align with that:

For Industry Radar Newsletters:

• Timely (breaking news or recent developments)

• Industry-specific (directly relevant to your niche)

• Impactful (has significant implications for your audience)

• Objective (presents factual information rather than pure opinion)

• Forward-looking (suggest potential consequences or next steps)

For Resource Curator Newsletters:

• High utility (provides tangible value to your audience)

• Comprehensive (covers the topic thoroughly)

• Accessible (can be understood and applied by your audience)

• Unique (not widely known or easily found elsewhere)

• Authoritative (comes from credible sources)

For Tactical Advisor Newsletters:

• Actionable (can be implemented relatively quickly)

• Specific (addresses a concrete problem or challenge)

• Efficient (provides good ROI for the time/effort required)

• Proven (has demonstrated results or is based on sound principles)

• Contextual (applicable to your audience's specific situation)

Feel free to use these or write up your own criteria! We’ll use them in the prompt below.

Setting Up Your AI Processing Workflow

Now, let's add an AI layer to the content collection system we built yesterday. Here's the basic workflow we're creating:

1. Content is automatically collected in your Google Sheet with status = "New"

2. Each morning, a scheduled automation identifies all "New" items and changes their status to "To Process"

3. Another automation sends all "To Process" items to AI for summarisation and evaluation

4. After processing, items are updated with summaries, scores, and status = "Processed"

5. A final automation creates a daily digest with the most promising items

For this setup, we'll use ChatGPT (either via API if you're technical, or manually if you're not). If you prefer Claude or another model, the same principles apply.

Option 1: Manual AI Processing (No Code Required)

If you're not comfortable with APIs or coding, you can still leverage AI effectively with a manual approach:

1. Create a simple filter view in Google Sheets that shows only items with status = "New"

2. Each morning, manually change these to "To Process"

3. Create a prompt template in a document you can easily access. The template should look something like this:

You are an expert content curator for a B2B newsletter focusing on [YOUR INDUSTRY/NEWSLETTER TYPE]. 

I'll provide you with a batch of content items. For each item, I need you to:

1. Create a concise 2-3 sentence summary capturing the key insights
2. Rate the item from 1-5 stars based on these criteria:
   [INSERT CRITERIA FOR YOUR NEWSLETTER TYPE FROM ABOVE]
3. Explain your rating in 1-2 sentences
4. Suggest a brief insight I could add if I featured this in my newsletter

Here are the content items to analyse:

ITEM 1:
Title: [TITLE]
Source: [SOURCE]
Content: [PASTE FULL CONTENT]

ITEM 2:
Title: [TITLE]
Source: [SOURCE]
Content: [PASTE FULL CONTENT]

4. Copy your "To Process" items from your Google Sheet and paste them into this prompt template.

5. Send the completed prompt to ChatGPT or your AI assistant of choice.

6. Copy the AI's response back into your spreadsheet, adding the summary, rating, and suggested insight to the appropriate columns.

7. Update the status of these items to "Processed"

8. Create a filtered view of all "Processed" items, sorted by rating (highest first)

This manual approach takes about 10-15 minutes each morning but saves considerably more time in review and selection.

I actually suggest starting with this to test out the quality of the output. Then when you are happy you can build it into the automatic flow.

Option 2: Semi-Automated Processing with Zapier

If you're comfortable with Zapier, we can create a more automated version. Here’s the basic flow:

1. Create a new Zap that triggers on a schedule (each morning at a set time).

2. Add a "Google Sheets" action to retrieve all items with "New" status from your content database.

3. Add a "Formatter" step to change their status to "To Process" and update the sheet.

4. Create a second Zap that triggers when a row is updated to "To Process" status.

5. Add a "ChatGPT" action (available on Zapier) and configure it with your API key.

6. Set up the prompt as shown above, mapping in the content items from your spreadsheet.

7. Add another Google Sheets action to update the row with the AI's analysis. This is where you map the AI outputs to specific columns in your sheet:

   • Summary field = AI-generated summary (you'll need to extract this from the AI response)

   • Rating field = AI-generated rating (extracted from response)

   • Insight field = AI-suggested insight (extracted from response)

   • Status field = "Processed" (static text)

   The extraction can be done using Zapier's Formatter tool with text parsing functions to pull out the relevant sections from the AI's response.

8. Add a final Google Sheets action to create a new row in a separate "Daily Digest" sheet that contains only the top-rated items (4-5 stars).

This approach requires more technical setup but runs automatically each morning with no additional input. Once built it’ll run everything for you.

Implementing the Workflow with Zapier

Let's implement this workflow using Zapier. We'll set up two main Zaps:

Zap 1: Daily Processing Trigger

1. Trigger: Schedule

   • Set this to run at a specific time each morning (e.g., 5:00 AM)

2. Action: Google Sheets - Find Many Rows

   • Set this to find all rows with Status = "New"

3. Action: Google Sheets - Update Multiple Rows

   • Update the Status field to "To Process" for all found rows

Zap 2: Content Analysis

1. Trigger: Google Sheets - New or Updated Spreadsheet Row

   • Set this to trigger when Status = "To Process"

2. Action: ChatGPT

   • Configure with your API key

   • Set up your prompt as described earlier, mapping in the content fields

3. Action: Google Sheets - Update Row

   • Update the row with the processed information as described above

   • Map the AI outputs to the appropriate columns

   • Set Status field = "Processed"

This setup automatically identifies new content, sends it for AI processing, and updates your database with structured, analysed content.

What Your Filtered Database Will Look Like

After implementing this system, your content database will transform from a chaotic collection of raw material into a structured, analysed resource.

Now you have a database where:

• Each content item has been analysed and summarised

• Quality ratings help you quickly identify the most promising content

• Explanations provide context for why items received their ratings

• The "Processed" status indicates these items have been through AI analysis

With this filtered database, you've dramatically reduced the noise and highlighted the signal. Instead of wading through dozens of full articles, you can now scan this structured table and quickly identify the most valuable content items.

At this point, you have a solid content filtering system:

• Automated content collection from multiple sources (Part 2)

• AI-powered analysis and evaluation (today)

• A structured database of processed content

BUT it’s still in a database which is a bit….busy!

Tomorrow in Part 4, we'll build on this foundation to create:

1. A daily digest that presents only the most promising items in an easy-to-review format

2. A system for selecting which content to feature in your newsletter

3. An automated process that transforms your selected content into a ready-to-send newsletter

Keep Prompting,

Kyle

If you feel this — learning how to use AI in entrepreneurship and work — is not for you → Unsubscribe here.