Boston Dato

Week 6 of the prompt engineering course is now done – and with it, the whole course.

Over six weeks ago, I started this course to better understand Artificial Intelligence, especially how it could connect to my current college education and my future in data analytics. The first three weeks focused on the fundamentals of prompt engineering and building from there. The second three weeks taught me how to turn this into something marketable, walking me through the basics of freelancing.

And now, having learned beyond the basics of prompt engineering and explored how to transfer those to freelancing, here I am. This final week was a combination of the course so far, looking at how to take the prompts that I’ve tweaked and engineered and turn them into a freelancing portfolio. The always-consistent ChatGPT broke this down into a simple series of steps to follow as I completed the weekly assignment.

1. About and Niche: A simple, two-sentence introduction to who I am and what audience I’m targeting
2. Sample Prompts: Assemble three sample projects from previous weeks’ work and pick out their goals, the processes I used, the output I got, and why they work
3. Client Workflow: Describe the ideal client workflow, including back-and-forth from describing their goal to the final output
4. Services and Pricing: Create a pricing model for my services, based less on experience (since I don’t have any) and more on speed and quality

Because this week was a combination of everything I’ve done thus far, I was able to assemble my work for this week from my work for previous weeks. For the first section, I wrote a simple bio introducing myself based on my client-friendly description from Week 4.

The next section, the sample products, I took three that I’ve worked on and simplified them, highlighting how they could work in various settings. I started with the student workflow process from Week 5, since this is my main product. I then revisited the infamous coffee shop pitch from Week 2, showing how a process could be used for an audience of investors. Finally, also from my practice of Week 2, I showcased how this could be used for small businesses wanting to roll out new products, highlighting the variety of types of outputs that could come from a workflow.

Following the sample products, I described a sample client workflow. It was pretty straightforward, but detailed enough so that clients and I can work closely to get the intended goal efficiently.
1. Client shares their goal – what they want to achieve and how I can help with that, getting as specific as possible
2. I design a custom prompt – using information from the client and previous examples, I design a prompt (or a series of prompts) to achieve an output
3. Client gives feedback for the output – after I review it myself, the client gives their own grading of the output
4. I refine the output – based on client’s feedback and my own personal notes, we go back and forth
5. Client and I agree on a final product – however long the feedback process takes, it ends with an agreement on a final product that excites both parties

Finally, I had to create a business model through services and pricing. After Week 4, I had created a barebones Fiverr profile to market my freelancing, with the goal of focusing on growing and updating it once this course ended. I was able to use this for my pricing.

After all of this, not just this week, but the course as a whole, where does that leave me? I think the best part of me going through this course is that, even if nothing happens from the freelancing, I learned a lot of useful skills that have already begun to help me as I interact with AI. These skills will continue to help me as a student, building on my tried-and-true study skills workflow. They will be especially valuable as I move into a professional career in a world becoming increasingly defined by generative AI and the gap between users and avoiders becomes more defined. And if the freelancing does pan out and I get to refine these skills while having an additional income source, then the benefits keep growing.

From here, I plan to refine my portfolio, further explore prompt engineering and utilizing AI, and see what freelancing could look like.

So, in short, learning through this course in the past couple of months has been helpful for multiple reasons. And for anyone who wants to go through a similar journey themselves, I would absolutely recommend it.

Final score: 20/20. It’s fitting that on the last week I finally earn a perfect score from the AI. ChatGPT will be getting a decent RateMyProfessor score after all.

If you want to see my full work, including the original prompts, results, and final essay, I’ve linked the Google Doc here.

We’re in the home stretch now, five weeks of the course down and only one more to go.

This week continued the pattern from last week of focusing more on the business side of freelance prompt engineering than the skill itself. My ever-faithful professor walked me through how to get my name out there as I’m starting out, from where to actually market myself, how to write a post and outreach messages, and building my portfolio to use as marketing. This seemed easy to me, so I jumped right in with the assignment, where I was tasked to do all of that for my own:

1. Create a simple marketing post directly for my audience
2. Write a short outreach message that’s more personable for direct clients
3. Assemble a sample output that I can share and present
4. The always-present reflection of transitioning from my previous projects to marketing myself

The marketing post was pretty easy, since I’m my own target audience. I shared where I was coming from, what inspired me to start this process, and laid out in simple terms what students would be getting from the final product and how it benefits them. The outreach message was also straightforward, especially since I could just build off of the marketing post. I condensed it and made it more personable, sharing my story with how I’ve used the workflow for myself and how it’s helped me.

Things got really interesting in the sample output. I decided that I wanted this to be an attention-grabbing poster, showing the full process with some quick examples. I started by opening up Google Drawings to design this myself, then quickly remembered that I am not, in fact, a graphic designer. I ended up creating a mini workflow of my own to design this poster.

I started by asking ChatGPT to inspire me and give me a basic outline for what would work well for this. I took this blurb, modified it, and gave it to Canva’s AI templates, but it couldn’t change the details. I gave the template that I liked the most to Claude and told it what I wanted to change. It natively created a new poster based in HTML, giving me exactly what I wanted. I was able to look at this poster, see something that I wanted to change, and tell Claude exactly what that was and it would get what I pictured, more or less.

As I begin to look forward to the end of this course and look back on what it’s taught me, I think the most important part is showcased in this coincidental discovery. Learning, especially with AI, takes time and practice, but once you know one skill, everything else builds on top of that. If I hadn’t learned how to be specific on the front end with AI models, than trying to design the template through Canva and the poster with Claude would not have ended well. If just browsing the internet nowadays hadn’t taught me to look carefully to see if something is real or AI-generated, I wouldn’t have checked for errors in the poster. The same skill stack will let me refine client deliverables and keep improving my services. All of this comes together to help me grow my brand and my knowledge, encouraging me as I look forward.

Next week, the final lesson, gets into the nitty-gritty of finding clients, including putting together a Fiverr profile for freelancing.

Final score: 19/20, both my marketing post and outreach message were too long. Again, I think it’s just nit-picky at this point.

If you want to see my full work, including the original prompts, results, and final essay, I’ve linked the Google Doc here.

Four weeks down, two more to go.

After passing the halfway point last week, the course switched from teaching me knowledge and skills to actually applying it all. Instead of learning how to take English-language requests and turn them into prompts, I now needed to turn my technical skills into easy-to-market pitches. To do this, ChatGPT walked me through a four-step lesson
1. Translate Skills into Client Language
2. Pick a Niche
3. Draft a Positioning Statement
4. Practice Framing a Service

After a little practice getting used to switching between technical jargon and common language, I jumped right in with the weekly project, following these skills for myself based on the student notes-to-summary workflow that I created last week. Here’s how I actually put these four steps into practice:

1. The Client-Friendly Description: I started by explaining what I do as if to someone who had never heard of ‘prompt engineering’. Since I was marketing to students, I wrote directly to them, describing what my systems do while emphasizing how it can make their lives easier.
2. The Target Market (Niche): Next, I explained why exactly I chose students as my target market. I realized that, not only would this be a good foundation since I know this audience well, it’ll give me the a launchpad for future experiences.
3. The Positioning Statement: From there, I drafted a simple positioning statement, a one-sentence, easy-to-read marketing pitch to simply explain what I do.
4. Framing My Service: To wrap it up, I turned it all into a full-length elevator pitch, giving a simple list of what exactly the workflow does and, more importantly, what it produces and how that helps students.

Even though this week was lighter than previous weeks, it was arguably the most valuable since it took steps to turn my knowledge into something practical (math teachers everywhere – take note). Each of these four steps were realistic, practical pieces for me starting my own freelancing journey, parts of a whole that I can carry with me as I move on from this course and into the real world of freelancing. Looking ahead to the final two weeks, these follow a similar course, giving me instructions to turn this into a real product and a portfolio worthy of future clients.

Next week specifically looks at building a portfolio and creating a brand from it, key steps for turning this into an actual gig.

Final score: 19/20, with half a point off for a lack of bullet points. Way to be nit-picky, ChatGPT.

If you want to see my full work, including the original prompts, results, and final essay, I’ve linked the Google Doc here.

Week 3 is now done and pushed my skills beyond what I already knew.

This week was all about combining the tools that I had been using individually to create a workflow for a potential client. I started by looking at various AI tools and their specialities, from ChatGPT and Gemini for text to MidJourney and DALL•E for images, and exploring how they could be combined. ChatGPT, my ever-faithful teacher, gave me a practice activity of having a client (another coffee shop; I think OpenAI is paid to advertise) who wants to create a system for product ideas.

This process allowed me to use the different prompting methods that I learned last week as I gave the chatbots examples to base their descriptions off of and created the workflow. After the practice, I started my own assignment that was near and dear to me – a student trying to be a better studier. Since I’m the target client, I tested it on my own notes and classes to see the results firsthand.

I started by defining the input from the student, trying to make it as simple as possible, and deciding to use a page of student-taken notes and the lesson slides. My goal was to use these to create a quick-and-easy review sheet with some practice questions, so that when the material comes back on a test, the student is ready to study.

Overall, this entire process was a lot more streamlined and user-friendly than I thought it would be. If I were to have other clients who required other outputs (images, code, etc.), then more complex tools would be needed, but this gave me a solid foundation to build off of. Once the process was finished, I immediately noticed the high potential for automation that this has, where automation tools can be used succinctly with the chatbots to minimize user input and time required for the workflow. Before turning this completely over to automation, I would have to work to clean up the prompts, making them as consistent enough to reliably get the desired results.

On the business side, this showed me how workflows can scale across different industries and how I can package them as services. It yet again proved how much potential freelancing has, especially if I’m able to create a portfolio’s worth of tools for multiple audiences, all of which are hands-off after the initial input and consistently create deliverable results.

Next week takes this practice and looks at how to turn the workflows into services that I can sell, emphasizing communication with the client.

Final Score: 18.5/20, with the points marked off because I didn’t show my work. Oh, the irony in a chatbot telling me to show my work.

If you want to see my full work, including the original prompts, results, and final essay, I’ve linked the Google Doc here.

Week 2 is in the bag, and it was exciting to get hands-on with prompt engineering and coffee shops.

This week was my first encounter of new content as I began to learn more than what I had casually done before. I started again by asking ChatGPT to teach me through Week 2 of the course, where it covered the five core prompting techniques, describing each and giving clear examples for how to use them:
– Zero-Shot, just asking the model (my natural prompting)
– One-Shot, giving the model one example
– Few-Shot, giving the model multiple examples (more is always better)
– Role-Based, assigning the model a role/position to work from
– Chain-of-Thought, asking the model to think step-by-step

For the weekly project, I was assigned to use all five techniques for the same pitch task (at this point, I’m pretty much an expert on pitching a coffee shop), analyze what each prompt gave me, and reflect on how useful each response was in general and for freelancing.

I found that the best techniques for freelancing were One-Shot and Few-Shot. These each required more work on the front end of finding well-crafted pitches that related to my end objective (callback to last week), but the end result was much closer to what I had in mind than the other techniques. Plus, as I keep using them, I get a portfolio of examples to give the model, helping my future self. Role-Based also worked well, but would require more back-and-forth with the model to fine-tune because it had a lot more variables.

So, what have I learned so far? I’ve gone a step further from basic prompting to learn the different styles and explored the strengths of each, helping me see which is the most useful for freelancing. I got reminded again that more work on the front end will always save time afterwards and can give you a leg up when working with clients. All of this came together to remind me that, even if I’m attempting to streamline with AI, doing something well means understanding it thoroughly and being willing to experiment, especially when working with a client. Marketing plans, writing prompts, coffee shop pitches (my strong suit), it all becomes easier the more often you do it and the more work you put into it.

Next week looks beyond simply interacting with ChatGPT and dives into the other tools that prompt engineers use, exploring both their uses for freelancing and general life.

Final Score: 19/20, a point off because I could have gone deeper on a topic in my prompt analyses. I actually agree with the robot on this one.

If you want to see my full work, including the original prompts, raw results, and final essay, I’ve linked the Google Doc here.

I’ll admit, using AI as a tool to teach me more about AI throws me off, but it is the expert on itself.

I started my coursework by switching to ‘Study’ mode and telling ChatGPT to use the curriculum that it had created and walk me through Week 1, which it titled “Introduction to Prompt Engineering & the AI Landscape,” a lesson heading that fits right in with my actual college courses. It walked me through the basics of prompt engineering, giving me questions or a ‘Try This!’ at the end of each section (which I definitely did, if the professor asks), and described how you can use the same prompt across different models and get different results, just based on what audience each model is tailored to.

Side note – it assigned a due date for the end of Week 1 and said that it would check in periodically as that approached. I completed it quickly, but now I’m wondering if it actually would have checked in on my progress. I’ll test that next week.

I decided to use ChatGPT – a familiar model – and Gemini – an unfamiliar one – and began my work. For the creative prompt, I asked the models to write a poem about watching the sunset as a hopeful young adult. My business prompt had them write a marketing email advertising a new hoodie line to veteran customers. And finally, the technical prompt, which was the most useful, was me asking the models to summarize a high-school physics lesson on buoyancy for a cramming student. The variety of topics let each model highlight its strengths.

With that in mind, I got to work, using the first prompts that came to mind. As a result, I was moved by artificially artistic poetry, persuasion to pay more than usual for a better hoodie, and stayed up late cramming for tomorrow’s physics exam.

Overall, ChatGPT was more concise than Gemini, giving the quick and simple answers that a modern teenager is most likely looking for. Throughout all three prompts, ChatGPT gave shorter responses that were more to-the-point than Gemini, showing that each model had its own uses: ChatGPT for the everyday user, and Gemini for more in-depth creation or research.

The two models primarily differed from each other in the physics summary prompt. ChatGPT gave a lesson that went over the content quickly and added practice questions. Gemini gave a full research study complete with a table on misconceptions and no practice problems. At first glance, ChatGPT would be declared the clear winner, but I realized that this is most likely user error on my end, where I switched Gemini to its ‘Research’ mode, overcomplicating the response from my original goal.

After one lesson from AI about itself, where does that leave me? Well, I learned that each model has its unique strengths and knowing what your intention or audience is can help you decide what model to use. The biggest takeaway is that being more specific from the beginning is always helpful when working with AI, regardless of the model. Specificity avoids confusion and frustration and saves time later on, even if it requires a couple more seconds on the front-end. It also reaffirmed that writing prompts isn’t just Googling – it takes work before, during, and after the model responds.

Next week takes this a step further, looking at what separates basic prompting techniques from advanced and how to use that in a variety of settings.

Final Score: 19.5/20, half a point marked off on the clarity of my analysis.
I think the professor has something against giving an A+.

If you want to see my full work, including the original prompts, raw results, and final essay, I’ve linked the Google Doc here.

Artificial intelligence is taking over the world.

Slightly drastic, but that seems to be the sentiment of literally everyone. That, or it’s going to save humanity. Generally speaking, I try to be more down-the-middle in my views about major topics (American politics don’t help with that). Rather than becoming too extreme one way or the other, I build my own opinion through research from multiple perspectives.

Through my own research on AI, I see it as a helpful tool. Can it take jobs? Sure, absolutely. Do we as people, citizens of the modern world, need to stop worrying about the end-all be-all worst case scenario and figure out how to use it beneficially? 100%. I try to see it more as the calculator. For anyone whose career depended on solving logarithms and graphing exponentials in calculus by hand, the calculator flipped their world upside down. But for the rest of us, we adapted to use it as an aid in our own research, giving more people than ever the ability to solve complex math and go further than humans had ever had access to. AI can do the same for another generation, if we focus on learning it instead of fearing its general existence.

A couple of weeks ago I started my freshman year at Miami University (of Ohio, a necessary clarification), majoring in data analytics and minoring in computer science. If you can’t tell from that sentence, or anything that I’ve written so far, I’m a proud nerd, and I always have been. This is why I am so interested in Artificial Intelligence, in learning about how exactly it works and how I can use it in my future.

Fueled by this intrigue, and by a desire to make some easy money as a student, I decided to start learning how to become a prompt engineer. Well, I found an article that described it as an easy side hustle, used ChatGPT to find out what exactly a prompt engineer does, and am now still using ChatGPT (among other intelligence models) to teach myself prompt engineering.

As I go through this self-guided course, I plan on using this blog to track my journey and record my milestones, as a way for me to reflect on my progress and to market myself in the future. This blog could be my personal gallery and my gateway to freelancing, or a random WordPress site that exists alone in the aether forever. No matter which it is, I’ll have learned something useful, and that’s what’s important.

But the supposedly easy money would be nice, too. Just throwing that out there.