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

👉 Grab a free project to learn about RAG in a practical way. 👈

Last year, I quit an AI startup where I helped build a multimodal RAG system and the agent layer of a production web app. Before leaving, I designed the interview process to hire my replacement — and the results were surprising.

In this video I break down what companies actually expect from an AI engineer, and why the role is usually less about training models and more about integrating LLMs into real products.

Most “AI engineer” jobs are really full-stack developers building AI-powered systems — agents, workflows, RAG pipelines, vector databases, evaluation frameworks, and observability.

I walk through what I expected candidates to know in the interview, including:

• Structured outputs

• Evaluating when AI systems are wrong (evals)

• Observability and tracing prompts/token costs

• RAG architecture and document chunking

• Metadata and data freshness

• Why re-ranking dramatically improves retrieval quality

I also share what happened when we caught candidates cheating during the interview — and the biggest gaps I saw between AI hype and real AI engineering.

This experience ultimately led me to build the Parsity AI Accelerator, focused on teaching developers how to build production AI systems rather than just prompting chatbots.

If you’re trying to become an AI engineer or preparing for AI interviews, this video will show you what actually matters.

If you're curious about Bryan's strategy, you can apply to work with him here: 👉 Application form.

The tech job market is brutal right now. Everyone knows it.

People are sending hundreds of applications, getting ghosted, and wondering what the hell is actually going on behind the scenes of hiring.

So in this episode I sat down with Bryan, someone I met on LinkedIn and later met up with in Reno, and he shared something that honestly blew my mind.

Last year he did what most people do:

Around 250 applications over 8 months… and almost no interviews.

This year he completely changed his approach.

Instead of blasting applications everywhere, he used a targeted strategy and applied to only 58 roles.

That turned into 16 interviews across 9 companies and multiple final rounds.

Yeah… that got my attention.

In this conversation we talk about what he’s seeing on the front lines of the hiring market, including:

• Why most resumes never get seen

• What hiring managers are actually filtering for

• The mistake developers make in behavioral interviews

• Why STAR stories matter way more than people think

• The reality of DSA interviews and why speed matters

• Why applying to the “right level” can dramatically increase your chances

• And why job searching is really a game of probability

If you’ve been applying to jobs and feel like everything is disappearing into a black hole, this episode should help you understand how the hiring game actually works right now.

And honestly, Brian’s story proves something important:

You don’t need hundreds of companies to say yes.

You just need one

In 2026, you can’t “avoid LinkedIn” and expect to get hired BUT you can't use it like 2023.

In this episode, I break down the exact LinkedIn + resume strategy I’d use today to maximize recruiter inbound, increase your surface area for luck, and stop making the most common mistakes that quietly kill your chances.

We cover:

• Why “Aspiring Junior Developer” and “Open to Work” often backfire

• How to make your first visible experience look software-related (even if you’re career-switching)

• The keyword/tech-stack problem that makes you invisible in recruiter search

• A simple formula to improve your resume

• Why “learn in public” is optional now—and what to do instead

• The fastest way to hit 500+ connections (without cringe networking)

• The 80/20 application approach: when to “Easy Apply” vs when to go aggressive

• Messaging tactics that stand out in a world of AI-generated slop

• A realistic volume target (and what to change if you’re getting zero responses)

If you want a practical plan to start getting interviews again—this is it.

Brian sits down with Fardeen Khimani, a 21-year-old Georgia Tech ML student and co-founder of Rounds, to talk about why technical interviews are broken and why AI just made it worse.

They cover why LeetCode is dying, why companies have no idea how to respond, and what skills actually matter now. Fardeen's take: if AI can pass an interview that maps to the real job, just hire the AI.

Find Fardeen: linkedin.com/in/fardeenkhimani

AI didn’t kill software jobs.

But it did throw a grenade into the hiring funnel.

In this episode, I break down 8 harsh truths about getting hired as a developer in 2026 — and none of them are the feel-good LinkedIn advice you’re used to hearing.

• Why vibe coding isn’t a career

• Why no one cares about your certificate

• Why your portfolio probably doesn’t matter

• Why full stack is now the baseline

• Why AI productivity claims are mostly nonsense

• Why waiting until you feel “ready” is killing your momentum

• Why titles matter more than people admit

• And why hiring is broken — but not hopeless

This isn’t theory. I’m sharing what I’ve seen as a hiring manager, what I’ve seen in interviews, and what I’ve seen work for developers I’ve mentored.

The market isn’t dead.

But the rules have changed.

If you want to land your first job — or level up in this AI-first world — you need to understand what actually matters now.

If you’re serious about switching careers and becoming a software developer, go to parsity.io or schedule a chat using the link in the show notes.

Disclaimer: this episode is my thoughts on coding bootcamps and online education and where Parsity is going in the future.

If you're interested in either of the programs I mentioned in this you can check them out here:

Parsity AI Accelerator

Full Stack Accelerator

Should you get a computer science degree, enroll in a coding bootcamp, or teach yourself how to code?

You’re probably not going to love the answer… but it depends.

In this episode, I shares my unfiltered, experience-backed take after working with hundreds of aspiring developers and hiring developers myself.

Let's breaks down what actually matters when trying to land your first software job — and where each path (college, bootcamp, or self-taught) helps or hurts.

• Why a college degree might help… but often not for the reason you think

• When bootcamps give you an edge — and where they fall short

• The uncomfortable truth about the “self-taught developer” myth

• How hiring really works at startups vs big tech companies

• Why fundamentals and computer science matter more later in your career

• How AI is changing the skills new developers need to stay employable

• The role of structure, accountability, and mentorship in actually getting hired

If you’re trying to break into software development and feeling overwhelmed by all the options, this episode will help you choose a path based on your time, money, learning style, and career goals — not hype.

If you are considering a coding bootcamp program, I encourage you to consider Parsity. Apply Here.