CodeBreakthrough - Caleb Curry

There is never ending discussion around AI, both against it and for it. My stance has always been quite neutral, I use AI when it makes sense. Instead of trying to either force it or resist it. I've been steadily using AI for the last few years as a learning assistant and more recently agentic AI the last 6 months.

This brings up a very important question, as a software engineer, what AI topics do I actually care about? Is this a fad or should I be investing time in learning AI?

A few years ago when studying AI you may have spent time learning Pandas, Scikit learn, machine learning, etc. While all that's great, most AI focus has shifted to LLMs and applied AI features within software applications, unless you're in a lower-level machine learning type of role.

Here's where to start:

Learn applied AI feature building. This can be done WITHOUT AI coding it for you. This is exactly what we did in the final 3 sections of Python Mastery. We build the entire pipeline by hand (except the frontend 😉)

I just finished the content of this course, so it's FRESH AI content. If you've been feeling a bit lost on what to focus on, this is a fabulous hands-on guide that is up-to-date.

You'll have a hard time finding modern applications that do not have some AI features: RAG, MCP, AI Chat bots, summarizations, generative tools, AI automations, etc. Failing to learn these things is just making your skills irrelevant.

TO BE CLEAR these skills are not just for "AI engineers" or something, they're features actively being built by software engineers and talked about all the time in job interviews. It's not some specialization, it's standard knowledge that you really need to start learning.

In these sections we learn how to run models locally and talk about:

• standardizations so you can easily swap to a platform API in production
• Running local models in with ollama and the different model types
• Connecting to models from Python and making prompts
• parsing and chunking .md documents and storing these in a vector db
• reading relevant data from the database for augmented prompting (RAG)
• Having AI models support users and learning through relevant sourcing from docs
• Building a simple chat bot that says where all the information comes from in the original markdown files.
• Track and display token usage both up and down

We do most of this manually, learning the fundamental systems instead of just plugging in some AI chatbot library that hides everything from us. This will give you the fundamental skill to better understand libraries like LangChain or LlamaIndex or ANY other library (again, focusing on the core skills).

Learn more in Python Mastery.

Agentic AI

Learning to use AI as a way to enhance your abilities is not only beneficial, but it's actually quite cool and fun. Start small and keep adding. Over the last 6 months I've experimented with antigravity, Claude Code, Codex, AI code reviews, AI design, etc. Some things worth learning:

• Skills - Summarize common actions in to a skill to easily bring that info in to context. For example, I have a skill for drawing diagrams, reviewing logs, review zoom meetings according to a sales framework, etc.
• Subagents - Describe tasks that can be done in isolation, created as needed. For example, a subagent to write tests or to run tests. I also created a linting agent that goes a bit deeper on vulnerabilities, licenses, etc.
• AI managed knowledge base - not just for documentation but business processes, standard procedures, and keeping track of components that can be used, etc. I do this through .md files and an obsidian vault.
• Dockerized agents, for giving up complete control without risking damaging your system or any sensitive services or data (this is what I've been experimenting with the most lately now that I'm pretty comfortable with the basics).

While we dont cover all of these things agentic AI topics in the Python course, I want to encourage you to get started experimenting. Instead of seeing it as a replacement to coding, you can actually learn both and enjoy both :)

30% off of the new Python Mastery is still live! Use code PYTHON at checkout.

Check it out here -> https://www.codebreakthrough.io/python-mastery​

Any questions just reply. but I also have a question for you. How are YOU using AI?

Caleb