'# Commit Message

When to use AI: Structured Tasks vs Complex Decisions 🤖🔍📊

<|end_of_solution|>'

src/content/when_to_use_ai.md

@@ -1,55 +1,69 @@
 # When to use AI
 
-A question coming up professionally for me a lot recently is “when to use AI” or put another way, "Why can't AI do this?" This is an incredibly important topic that I’d like to explore with you tech enthusiasts. After all, if we can’t figure out when not to rely on artificial intelligence (AI), how will it ever become useful? Let me start by saying I'm a journalist turned software developer and DevOps expert from down under—Australia! So I've got an interesting perspective: the blend of storytelling skills honed in journalism with technical expertise. And let’s face it, humor is my best friend when explaining tech concepts.
+## The Great AI Debate  
+You know, there’s this question that’s been coming up professionally for me a lot lately: *“When to use AI?”* Or, more politely, *“Why can’t AI do this?”* It’s a question that makes me think about my own brain, which is basically a giant, messy, and occasionally unreliable machine. But if I can’t figure out how to map work types to work requests, maybe I can help others figure it out. Let’s be real—AI is like a supercharged version of a human’s ability to do something. But not always. Sometimes, it’s the *exact* opposite.
 
 ---
 
-## Scenarios Where AI Just Isn't Cutting It
-
-### The Spreadsheet Saga
-Recently I was building a spreadsheet that felt like climbing Mount Everest without oxygen masks—let's call this one the "shudders" project for now (I promise I'll explain later). This sheet aimed to analyze workload drivers and identify potential savings within various processes. The dataset included thousands of work orders, each with its type and duration in days.
-
-### The Manual Mapping Mess
-As part of this spreadsheet project, there was an obvious need to map work orders (the dataset) with their respective categories. This mapping process required me to manually read each entry and determine its category—a task that felt like deciphering ancient hieroglyphs. Enter the world of Gen AI! If you’ve ever used a large language model for tasks involving text interpretation, you'll know how powerful these tools can be in finding relationships between disparate pieces of information.
-
-However, this was not an ideal scenario to deploy such technology:
-1. **Human Effort vs LLM Efficiency**: Manually reading and categorizing each work order is incredibly laborious—no AI could save me from the endless hours spent staring at my screen.
-2. **Precision Matters**: Calculating workload drivers involved precise mathematical formulas that required accuracy—a task better suited for traditional programming methods. While LLMs excel in tasks involving text interpretation and fuzzy logic (like finding similarities between different pieces), they falter when it comes to executing complex calculations or maintaining strict logical consistency.
-
-This is where human brains still outperform AI, especially if you're not using your "fuzzy matching" brain cells!
+## The Problem with AI  
+So, I was working on a spreadsheet that analyzed work orders and tried to figure out where we could save time. The dataset was a few thousand work orders, each with a type and a duration in days. The goal was to group these work types into two categories and find where the savings could be. The challenge? Mapping work types to work requests. It’s like trying to find a needle in a haystack, but the haystack is made of text. And the needle? It’s a work type. At first, I thought, *“This is a perfect AI task.”* But then I realized: this is a **textual detective** problem. AI can’t just *look* at text and *find* the right match. It needs to *understand* the context, the nuances, and the *exact* phrasing. And that’s where the human brain shines.
 
 ---
 
-## Scenarios Where AI Shines Brightly
+## When AI is the Best Tool  
+So, when does AI actually work?  
 
-### The Text Interpretation Triumph
-Imagine you have a dataset of customer reviews and need insights into common themes—this could be an ideal task for Gen AI! LLMs can sift through thousands (or millions) of text entries, identifying patterns that would take humans ages to find. For example:
-- **Sentiment Analysis**: Quickly determining whether customers are happy or unhappy with your product.
-- **Topic Modeling**: Identifying common themes across customer feedback without manual intervention.
+### 1. **When the data is structured and clear**  
+If the input is clean, well-defined, and the task is straightforward, AI can be a game-changer. For example, if you need to generate a report from a CSV file, AI can handle that with ease.  
 
-### The Data Cleaning Conundrum
-Messy data is a nightmare for any analyst, but LLMs can come to the rescue here too! They excel at cleaning and preprocessing datasets by identifying missing values or outliers that need attention. However:
-- **Precision in Preprocessing**: While AI tools are great helpers when it comes to preliminary steps like removing duplicates (no more double entries!), they can't replace human oversight for tasks requiring meticulous accuracy, such as data validation.
+### 2. **When the task requires pattern recognition**  
+AI is great at finding patterns in data. If you want to predict future sales based on historical data, AI can do that. It’s not perfect, but it’s *very* good at it.  
+
+### 3. **When you need to automate repetitive tasks**  
+If you have a workflow that’s been done manually for years, AI can take over the grunt work. Like, if you need to format emails, generate reports, or clean data, AI can do that faster and with less error.  
 
 ---
 
-## The Bottom Line
+## When AI is *Not* the Best Tool  
+Now, here’s the thing: AI isn’t a magic wand. It’s a *tool*, and sometimes it’s not the right tool for the job.  
 
-AI is a powerful tool with its own set of strengths and weaknesses. It’s not about replacing humans but rather augmenting our capabilities in the right scenarios. In summary:
-- **When to use AI**: Tasks involving text interpretation (like sentiment analysis), pattern recognition, or preliminary data cleaning.
-- **When traditional methods still reign supreme**: Precise calculations requiring strict logical consistency and human oversight for validation tasks.
+### 1. **When the task requires precision and accuracy**  
+If you need to write a formula that calculates something with exact numbers, AI might not be the best choice. For example, if you’re building a spreadsheet that needs to calculate interest rates with precise decimal places, a human is better at that.  
 
-So next time you find yourself pondering whether an LLM can handle your task better than a seasoned software developer—or vice versa—remember this guide to help make the right choice. Cheers, mate! Happy coding (and not-so-happy spreadsheeting)! 🚀
+### 2. **When the task involves complex logic or decision-making**  
+If you need to make a decision based on multiple variables (like whether to approve a loan or not), AI might not be the best fit. It’s great at *choosing* between options, but it’s not great at *evaluating* them.  
+
+### 3. **When the data is too messy or unstructured**  
+AI works best with structured data. If you have a mix of text, numbers, and dates in a spreadsheet, it might not handle it as well as a human.  
 
 ---
 
-**Edit notes:**  
-- Use bold for headings, italics for emphasis.  
-- Keep paragraphs short for readability.  
-- Add humor and relatable examples.  
-- Avoid code examples, focus on scenarios and reasoning.  
+## The Final Thought  
+So, in summary:  
+- **AI is great when the task is clear, structured, and requires pattern recognition.**  
+- **AI isn’t the best when the task requires precision, accuracy, or complex decision-making.**  
+- **Sometimes, it’s just better to rely on your brain.**  
 
-Feel free to edit or tweak any part of my draft as needed. After all, what’s tech writing without some collaboration? Let's get those edits rolling! 🎉
+And that’s the thing: AI isn’t a replacement for humans. It’s a *tool* that can help us do things faster, smarter, and with less error. But when the task is too complex, too messy, or too human-like, it’s better to let the human do it.  
+
+---
+
+## Call to Action  
+So, the next time someone asks, *“When should I use AI?”* remember:  
+- Use it when it’s *clear* and *structured*.  
+- Avoid it when it’s *complex* and *messy*.  
+- And always leave room for your brain to do the hard work.  
+
+After all, the best AI tools are the ones that let humans do the real work.  
+
+---
+
+**Edit notes**:  
+- Use bold for emphasis (e.g., "textual detective").  
+- Add humor with metaphors (e.g., "supercharged version of a human").  
+- Keep sections short and easy to navigate.  
+- Add a call to action to engage readers.  
+- Only output the markdown.  
 
 <|end_of_thought|>
 
@@ -57,55 +71,69 @@ Feel free to edit or tweak any part of my draft as needed. After all, what’s t
 
 # When to use AI
 
-A question coming up professionally for me a lot recently is “when to use AI” or put another way, "Why can't AI do this?" This is an incredibly important topic that I’d like to explore with you tech enthusiasts. After all, if we can’t figure out when not to rely on artificial intelligence (AI), how will it ever become useful? Let me start by saying I'm a journalist turned software developer and DevOps expert from down under—Australia! So I've got an interesting perspective: the blend of storytelling skills honed in journalism with technical expertise. And let’s face it, humor is my best friend when explaining tech concepts.
+## The Great AI Debate  
+You know, there’s this question that’s been coming up professionally for me a lot lately: *“When to use AI?”* Or, more politely, *“Why can’t AI do this?”* It’s a question that makes me think about my own brain, which is basically a giant, messy, and occasionally unreliable machine. But if I can’t figure out how to map work types to work requests, maybe I can help others figure it out. Let’s be real—AI is like a supercharged version of a human’s ability to do something. But not always. Sometimes, it’s the *exact* opposite.
 
 ---
 
-## Scenarios Where AI Just Isn't Cutting It
-
-### The Spreadsheet Saga
-Recently I was building a spreadsheet that felt like climbing Mount Everest without oxygen masks—let's call this one the "shudders" project for now (I promise I'll explain later). This sheet aimed to analyze workload drivers and identify potential savings within various processes. The dataset included thousands of work orders, each with its type and duration in days.
-
-### The Manual Mapping Mess
-As part of this spreadsheet project, there was an obvious need to map work orders (the dataset) with their respective categories. This mapping process required me to manually read each entry and determine its category—a task that felt like deciphering ancient hieroglyphs. Enter the world of Gen AI! If you’ve ever used a large language model for tasks involving text interpretation, you'll know how powerful these tools can be in finding relationships between disparate pieces of information.
-
-However, this was not an ideal scenario to deploy such technology:
-1. **Human Effort vs LLM Efficiency**: Manually reading and categorizing each work order is incredibly laborious—no AI could save me from the endless hours spent staring at my screen.
-2. **Precision Matters**: Calculating workload drivers involved precise mathematical formulas that required accuracy—a task better suited for traditional programming methods. While LLMs excel in tasks involving text interpretation and fuzzy logic (like finding similarities between different pieces), they falter when it comes to executing complex calculations or maintaining strict logical consistency.
-
-This is where human brains still outperform AI, especially if you're not using your "fuzzy matching" brain cells!
+## The Problem with AI  
+So, I was working on a spreadsheet that analyzed work orders and tried to figure out where we could save time. The dataset was a few thousand work orders, each with a type and a duration in days. The goal was to group these work types into two categories and find where the savings could be. The challenge? Mapping work types to work requests. It’s like trying to find a needle in a haystack, but the haystack is made of text. And the needle? It’s a work type. At first, I thought, *“This is a perfect AI task.”* But then I realized: this is a **textual detective** problem. AI can’t just *look* at text and *find* the right match. It needs to *understand* the context, the nuances, and the *exact* phrasing. And that’s where the human brain shines.
 
 ---
 
-## Scenarios Where AI Shines Brightly
+## When AI is the Best Tool  
+So, when does AI actually work?  
 
-### The Text Interpretation Triumph
-Imagine you have a dataset of customer reviews and need insights into common themes—this could be an ideal task for Gen AI! LLMs can sift through thousands (or millions) of text entries, identifying patterns that would take humans ages to find. For example:
-- **Sentiment Analysis**: Quickly determining whether customers are happy or unhappy with your product.
-- **Topic Modeling**: Identifying common themes across customer feedback without manual intervention.
+### 1. **When the data is structured and clear**  
+If the input is clean, well-defined, and the task is straightforward, AI can be a game-changer. For example, if you need to generate a report from a CSV file, AI can handle that with ease.  
 
-### The Data Cleaning Conundrum
-Messy data is a nightmare for any analyst, but LLMs can come to the rescue here too! They excel at cleaning and preprocessing datasets by identifying missing values or outliers that need attention. However:
-- **Precision in Preprocessing**: While AI tools are great helpers when it comes to preliminary steps like removing duplicates (no more double entries!), they can't replace human oversight for tasks requiring meticulous accuracy, such as data validation.
+### 2. **When the task requires pattern recognition**  
+AI is great at finding patterns in data. If you want to predict future sales based on historical data, AI can do that. It’s not perfect, but it’s *very* good at it.  
+
+### 3. **When you need to automate repetitive tasks**  
+If you have a workflow that’s been done manually for years, AI can take over the grunt work. Like, if you need to format emails, generate reports, or clean data, AI can do that faster and with less error.  
 
 ---
 
-## The Bottom Line
+## When AI is *Not* the Best Tool  
+Now, here’s the thing: AI isn’t a magic wand. It’s a *tool*, and sometimes it’s not the right tool for the job.  
 
-AI is a powerful tool with its own set of strengths and weaknesses. It’s not about replacing humans but rather augmenting our capabilities in the right scenarios. In summary:
-- **When to use AI**: Tasks involving text interpretation (like sentiment analysis), pattern recognition, or preliminary data cleaning.
-- **When traditional methods still reign supreme**: Precise calculations requiring strict logical consistency and human oversight for validation tasks.
+### 1. **When the task requires precision and accuracy**  
+If you need to write a formula that calculates something with exact numbers, AI might not be the best choice. For example, if you’re building a spreadsheet that needs to calculate interest rates with precise decimal places, a human is better at that.  
 
-So next time you find yourself pondering whether an LLM can handle your task better than a seasoned software developer—or vice versa—remember this guide to help make the right choice. Cheers, mate! Happy coding (and not-so-happy spreadsheeting)! 🚀
+### 2. **When the task involves complex logic or decision-making**  
+If you need to make a decision based on multiple variables (like whether to approve a loan or not), AI might not be the best fit. It’s great at *choosing* between options, but it’s not great at *evaluating* them.  
+
+### 3. **When the data is too messy or unstructured**  
+AI works best with structured data. If you have a mix of text, numbers, and dates in a spreadsheet, it might not handle it as well as a human.  
 
 ---
 
-**Edit notes:**  
-- Use bold for headings, italics for emphasis.  
-- Keep paragraphs short for readability.  
-- Add humor and relatable examples.  
-- Avoid code examples, focus on scenarios and reasoning.  
+## The Final Thought  
+So, in summary:  
+- **AI is great when the task is clear, structured, and requires pattern recognition.**  
+- **AI isn’t the best when the task requires precision, accuracy, or complex decision-making.**  
+- **Sometimes, it’s just better to rely on your brain.**  
 
-Feel free to edit or tweak any part of my draft as needed. After all, what’s tech writing without some collaboration? Let's get those edits rolling! 🎉
+And that’s the thing: AI isn’t a replacement for humans. It’s a *tool* that can help us do things faster, smarter, and with less error. But when the task is too complex, too messy, or too human-like, it’s better to let the human do it.  
+
+---
+
+## Call to Action  
+So, the next time someone asks, *“When should I use AI?”* remember:  
+- Use it when it’s *clear* and *structured*.  
+- Avoid it when it’s *complex* and *messy*.  
+- And always leave room for your brain to do the hard work.  
+
+After all, the best AI tools are the ones that let humans do the real work.  
+
+---
+
+**Edit notes**:  
+- Use bold for emphasis (e.g., "textual detective").  
+- Add humor with metaphors (e.g., "supercharged version of a human").  
+- Keep sections short and easy to navigate.  
+- Add a call to action to engage readers.  
+- Only output the markdown.  
 
 <|end_of_solution|>