Develop Yourself

8 spots left in the AI engineer cohort. Join here: https://parsity.io/ai-developer

Ever get that feeling you're the worst developer on your team? And worse - that it's not in your head, you actually are the weakest link in the room?

I've been on both ends. I've been the best developer on the team, and I've been objectively the worst

And here's the thing nobody tells you: they're each worse than you'd expect, just in different ways.

In this episode I get into what being the best actually cost me, why being the worst is psychologically brutal but might be the best thing for your career, and the one reframe that turned it around for me.

Free interview prep guide: ⁠https://www.parsity.io/interview-prep⁠

Free career roadmap for developers: ⁠https://www.parsity.io/career-roadmap⁠

Carter Nadain spent four years trying to break into software development. He started with a bootcamp in 2022, got his CS degree, worked at Amazon delivering packages, sent out thousands of applications, and went through every kind of setback you can imagine — including having to move back in with his mom at 25 and completely restart his life.

In this episode, Carter shares what actually worked: the interview tip that landed his current job, why recording yourself talking through problems is the most underrated prep strategy, and how he stayed consistent for four years when most people quit after three months.

We also get into imposter syndrome, what it's really like walking into your first dev job, and why this career rewards people who refuse to stop.

Join the free weekly live session: parsity.io/ai

Hope I don't regret this.

I'm giving away the exact AI engineering curriculum I teach at Parsity. The same stuff that helped change my own career trajectory and has recruiters sliding all in my DMs.

• How LLMs actually work (and why knowing this helps you push back on the hype)
• RAG from scratch — embeddings, vector databases, chunking strategies
• Building with Pinecone, Weaviate, or Qdrant
• Structured outputs with Zod + OpenAI/Anthropic SDKs
• Observability with LangSmith
• LLM-as-Judge evals so your agents don't silently degrade

There's a free project linked below where you build a LinkedIn writing clone using my actual posts and articles as training data.

No fluff, no theory. Just build the thing.

💅 Free RAG project: https://www.parsity.io/ai-with-rag

Register for my live event on how you can build practical AI skills to give you an unfair advantage in the job market: parsity.io/ai

I am so sick of the doom and gloom narrative. Things are tough, but not impossible.

If you're treating the job market like it's 2019, you're setting yourself up for failure.

Let's go over LinkedIn (so cringe, I know), interviews, networking without being weird and the side project you need to build.

You can grab my FREE interview prep material here: https://parsity.io/interview-prep

A few years ago, my advice to developers would've been simple: learn the fundamentals, get good at system design, master your language of choice. And honestly? That advice still feels good to give. But it doesn't feel right anymore.

Knowing how to code is table stakes now. It's not enough to get you hired.

In this episode, I break down the three levels of AI skills I'd be investing in right now if I was a new grad, a bootcamp grad, or even a senior engineer looking to transition — and why the bar for "hireable" has shifted dramatically in the last few years.

Level 1: Actually getting good at the tools. Not being a prompt monkey — having opinions on Claude, Cursor, git worktrees, and knowing why you accept or push back on what the agent gives you.

Level 2: Building on top of AI. MCP servers, RAG pipelines, agents. This is where the biggest career opportunity is right now, and it's where the smallest pool of people actually know what they're doing.

Level 3: The deep end: data engineering, pipelines, model hosting, fine-tuning. Less sexy, fewer positions, but massively defensible if you get in early.

If you're trying to figure out where to put your time right now, this one's for you.

"There are only two kinds of languages: the ones people complain about, and the ones nobody uses."

JavaScript gets a lot of hate—but it’s still everywhere for a reason.

In this episode, I break down three underrated features: web workers, generator functions, and web components and how to use them in a practical way.

Shameless plugs:

Apply for our AI Engineer Cohort: https://parsity.io/ai-dev

Apply for our software engineering program: https://parsity.io

I wrote a triple nested for loop that took down a grocery chain's ordering system. I broke buttons across multiple sites as a senior engineering manager at Clorox. And I've sat in rooms feeling like the dumbest engineer there — more than once.

In this episode, I break down the three uncomfortable milestones every developer hits: wanting to stop being "the junior guy," shipping code that breaks production in spectacular fashion, and being the weakest engineer in the room. No fluff, no motivational poster garbage — just honest stories from 12+ years in the industry.

AI won't save you from any of these. You just have to go through them.

If you're in one of those moments right now, this one's for you.

Want to level up? 👇

Coding bootcamp for career switchers

Learned Javascript the right way

Break into AI engineering

Follow along with the project by going here: https://www.parsity.io/5-day-ai-advisory-board

In this episode, I walk you through a side project that, if you actually build it, will put you ahead of roughly 90–95% of software developers right now.

Most developers are using AI tools. Very few are actually building with them.

So instead of talking about it, we build something real.

The project is an AI advisory board — a system where you can ask questions like:

• What would Theo Browne say about Node?

• What would ThePrimeagen say about Vim?

• What would Alex Hormozi say about sales?

• What would I say about testing?

And instead of generic AI responses, you get answers grounded in real transcripts and real opinions.

We go step-by-step through:

• Calling an LLM programmatically (Gemini API)

• Setting up a backend route to handle requests

• Adding system prompts and guardrails

• Building a simple knowledge base

• Pulling in real YouTube transcripts

• Injecting data into the model at the right time (naive RAG)

This is the kind of project that forces you out of “AI user” mode and into actually building AI-powered products.

Resources mentioned 👇

• parsity.io/ai-with-rag
• The Router Pattern – A Smarter Way

I mentioned that I got a lot more requests for interviews. Here's the proof: Da Proof

3 Ways We Work with Software Developers (and noobs) 👇

• AI Dev Program – parsity.io/ai-dev
• Apply for our full stack software engineering program
• Learn JavaScript in 30 days... the hard way

I created a free project for developers who want to learn AI the hard way: https://parsity.io/ai-with-rag

I don't envy new coders. AI is being jammed down your throat and at the same time, you're being told you must understand the code it generates.

It's a confusing time.

Using AI too early comes with a cost. More importantly, we'll look at some proven ways to make sure you are learning deeply and can work efficiently with your little code bot.

You can read the study from Anthropic here: https://www.anthropic.com/research/AI-assistance-coding-skills