🆓 Is AI Going to Take My Job?
It's natural to feel like you're being pushed out of the tech world. It's true: AI can do a lot of the boring stuff we used to do, but I like to focus on the word "boring". It's kind of nice to not be bored, isn't it?
· Rob Conery
LAB: Preparing for Open Source
This is the final step for us for this workshop! We'll be using Copilot and Claude Sonnet one more time because I've found it writes the most complete markdown documents. Gemini's terseness is great, but having a full, rounded set of docs is even better.
· Rob Conery
LAB: AI, Review Yourself
It turns out that AI can plan your spec, create your database schema, write your data access code, and then write some of your app's logic. Oh yeah: it can also review its own work.
· Rob Conery
LAB: Writing Tests First
Writing code is what we do, and it's the fun part of being a programmer. Writing shopping cart code, however, might fall into that "boilerplate" category. There's just not much to figure out. Let's make Gemini do it.
· Rob Conery
LAB: Updating Our Spec
AI tools aren't just for code generation - they can refactor things as well, including our project spec.
· Rob Conery
LAB: Using Templates
This is where the fun truly begins. We're going to combine all the things we've learned in this session to create a simple data access layer for our project, complete with tests.
· Rob Conery
LAB: Adding Style Guides
Letting your AI tool decide how to code things is like letting a stranger on the street dress you in whatever fashion they like. Not gonna happen! So let's make sure we're on fleek with our LLM.
· Rob Conery
LAB: Create an Initial Spec
LLMs are exceedingly good at handling "boilerplate" code, which usually applies to things like data access, mapping records to objects, and commonplace logic like shopping carts.
· Rob Conery
LAB: Improving The Git Commit Message
In the last session we used Gemini CLI to create a commit message for us, but the prompting process took longer than just writing the message ourselves. Do we have to do this every time we need a commit message? Hopefully not, it's too much work.
· Rob Conery
LAB: Building Better Context With Instructions
In this session we're going to fine tune our AI tools to make the answers we get back more relevant, and the prompts we write much shorter. It's amazing what you can do with some extra context!
· Rob Conery
LAB: Write Me a Compiler Script
In this lab we'll see how this works, and using a little inception, I'll show you how I resized the images to layout properly on the page, and how to compile markdown documents into whatever output you like.
· Rob Conery
LAB: Let AI Write Your Commit Message
In this lab we'll be using Gemini as we're going to revisit this topic in a later session on using instructions and for that, we'll be using VS Code.
· Rob Conery
LAB: Setting Up a Project
Getting a project off the ground can be a simple process. Too simple. It's incredibly easy overlook the simple things that will get us in to hot water later on.
· Rob Conery
LAB: How Do I…?
As programmers, we have learned how to expertly search Google for any given problem. We've even learned how to "ask the right question" to maximize the search results.
· Rob Conery
🆓 LAB: Installing Your Favorite Tool
For this lab, it's not necessary that everyone have the same tool installed. Each one is different, but that said, they all do the same basic thing.
· Rob Conery
A Quick Discussion on Premium Tools
Paying for an AI coding tool is a simple decision: it's well worth the money. A good AI coding tool will save you ridiculous hours writing boilerplate code, shell scripts, commit messages, and generating the commonly used files your project needs, such as a README.
· Rob Conery
🆓 Defining the Jargon
We'll be throwing some terms around in this workshop, which you should become familiar with. AI tools, up until now, were created by engineers with almost zero product and marketing help, which means the naming is completely arbitrary and meaningless, in most cases.
· Rob Conery
🆓 Adjusting Your Mindset
It's easy to feel disoriented when you first start working with AI coding tools. It feels like they're doing a large part of your job for you, which is never fun, because coding is fun - isn't it?
· Rob Conery
🆓 The Tools You Will Need
AI is a giant data model running on the servers of whatever company created it. The tools are what you and I use every day - the CLI, Editor extensions, or even the editor itself. Let's install the ones we like.
· Rob Conery
Asking Questions, Getting Answers
In this video we'll take a quick tour of AI tooling as of the writing of this workshop. Things will change and I can guarantee you won't see the same things today that you'll see in this video.
· Rob Conery
Welcome to the Wild West (and your downloads)
Welcome to the workshop! If you're taking this on your own, you can go at your own pace and experiment as you will, which I highly encourage. Working with AI is one of those things that will blow your mind, make you super excited, then afraid, and then curious.
· Rob Conery
FREE: You're Ready. Now Go Build Something.
You've got the techniques. You've got the tools. The only thing left is to use them. Go make something real.
· Rob Conery
LAB: ETL With Claude, Fake Data, and a Sci-Fi Obsession
Generate fake data, validate it, and analyze it, using Claude to write every script. The prompt engineering trick is the point.
· Rob Conery
Using Make to Improve Your Test Suite
No video with this one - just a post with lots of code. Make has been around forever and is often overlooked in favor of tools that recreate precisely what it does, but in crappier ways. Let's see how you can use Make to help your testing process.
· Rob Conery
Transform Messy Data Without Writing Transformers
ETL is tedious. Mapping fields, handling edge cases, validating output. Let the AI do the boring parts while you focus on what matters.
· Rob Conery
Wrapping Up
We're all done - but was it worth it? Being honest: both yes, and no.
· Rob Conery
Making Your Life Easier with Make
Make is a build utility that works with a file called a Makefile and basic shell scripts. It can be used to orchestrate the output of any project that requires a build phase. It's part of Linux and it's easy to use.
· Rob Conery
Skip the Pandas Tutorial
You don't need to learn a data analysis library to answer questions about your data. Describe what you want and let Claude write the code.
· Rob Conery
Setting Up S3 CDN
We don't want our CMS images served from our disk in production, so we need to set up a CDN. I'll use S3 as that's what I know.
· Rob Conery
Testing with Playwright
I've avoided testing until now - let's fix that.
· Rob Conery