This blog is the second post in my series “From Solution Architect to AI Architect” where I document my learning journey step by step. My goal is simple: to build the skills I need to design, prototype, and evaluate AI systems confidently and to share that journey with anyone walking a similar path.
During my first week of the learning plan, I decided to start with something foundational: a Python refresh. Even though I’ve used Python here and there, on small personal projects, quick scripts, and a few professional tasks, my experience was inconsistent. Enough to get things done, but not enough to call myself a comfortable or fluent Python developer. I’m probably somewhere between beginner and intermediate.
So, I set aside a few hours to review the basics and catch up on anything I had missed. I chose the Learn Python with AI course. It’s well structured, easy to follow, and you can skip ahead anytime you already understand a concept.
Here’s how the course is structured:
- Module 1: Basics of AI Python Coding
- Module 2: Automating Tasks with Python
- Module 3: Working with Your Own Data and Documents in Python
- Module 4: Extending Python with Packages and APIs
The first two modules are perfect for complete beginners or people learning their first programming language. The first module is extremely basic: variables, simple types, and loops. If you’ve coded in any language before, you’ll likely breeze through it. I watched a minute or two per lesson, confirmed I knew the content, and moved on. If you already have experience with any modern language, you can safely skip most of them and focus on Modules 3 and 4.
One thing I appreciated is that the course uses Jupyter Notebooks directly in the browser. I prefer working in my own environment, so I ran the notebooks in VS Code using the Jupyter extension. It makes the workflow smoother and feels more like “real” development.
What makes this course a bit different is that it doesn’t just teach Python; it also teaches you how to use LLMs like ChatGPT as part of your learning workflow. You’re encouraged to ask the model for examples, explanations, comparisons, debugging help, or even code rewrites. It’s a nice blend of traditional learning and AI assistance, and honestly, it makes the process more enjoyable.
Things really get interesting in Module 3, where you begin manipulating files, parsing text, extracting information, and working with your documents. This is where Python reveals its true value for anyone transitioning into AI work, especially when prototyping data pipelines, cleaning text, or preparing datasets.
The final module brings everything closer to real-world engineering. It shows how to install and use external Python packages, integrate libraries you didn’t write, and interact with APIs, including AI model APIs. This is where you start sending prompts programmatically, receiving responses, and processing outputs.
Overall, this course wasn’t a deep dive into Python, but it was an enjoyable and worthwhile refresher. It cleared out the rust, filled a few gaps, and reminded me why Python is such a powerful language. More importantly, it set me up for the next steps in my journey toward becoming an AI Architect.