Podcast · Tech & Science
by Kaushik Gopal, Iury Souza · English · Tech & Science
Fragmented is an AI developer podcast for engineers who want to go beyond vibe coding and ship real software. We cover AI-assisted development the way working engineers actually use it: prompting strategies, code review, testing, debugging, workflows, and building production-grade software with…
6 Sep 2026 · 13 min
Claude Code and Codex have been the mainstay. OpenCode and Pi showed what open-source harnesses could be. But two new entries just moved the goalposts: DeepSeek's Cordis kernel treats everything — even the agent loop itself — as a hot-swappable plugin, and Prime Agent runs the whole harness inside a live REPL where sub-agents are just function calls. Self-learning harnesses are here, and they're open source.
E310 · 14 Apr 2026 · 1 hr
Mitchell Hashimoto co-founded HashiCorp, built some of the most impressive DevOps tools like Vagrant and Terraform, sold the company to IBM — and then built a terminal. Ghostty is now where a huge chunk of agentic coding actually happens. Mitchell was an AI skeptic. We walk through his six-step adoption framework and the workflows he uses day to day — warm-start research, Hail Mary prompts across twenty GitHub issues, and knowing when to let the agent slam dunk it. Full shownotes at https://fragmentedpodcast.com/episodes/310/
E309 · 1 Apr 2026 · 26 min
Andrej Karpathy says the goal is to maximize how long an agent runs without your intervention. But there's a false summit most teams hit first: individual speed goes up while system speed stalls, your laptop roars under four parallel Gradle builds, and review queues back up. Kaushik and Iury trace the full arc — from local multitasking to cloud-hosted async work to fully autonomous agents that fire on repo events and put PRs in your inbox. Full shownotes at https://fragmentedpodcast.com/episodes/309
E308 · 24 Mar 2026 · 25 min
You already know how LLMs work from our popular 20-minute explainer. Now we take it to images. What does Michelangelo have to do with stable diffusion? More than you'd think. Walk away knowing how image generation actually works — and what it has in common with the text models you already understand. Full shownotes at https://fragmentedpodcast.com/episodes/308/
E307 · 17 Mar 2026 · 30 min
The hard part of AI coding isn't generating code — it's controlling quality, safety, and drift. Kaushik and Iury break down harness engineering: the five pillars for shaping an agent's environment and what it looks like when teams build custom harnesses from scratch. Full shownotes at - https://fragmentedpodcast.com/episodes/307
E306 · 10 Mar 2026 · 23 min
AGENTS.md is becoming the common language for AI coding tools, but keeping repo rules, personal rules, and tool-specific files in sync is still messy. In this episode, Kaushik and Iury break down the sync problem, compare their own setups, and unpack what the latest AGENTS.md research actually says. Full shownotes at https://fragmentedpodcast.com/episodes/306/
E305 · 17 Feb 2026 · 27 min
Subagents are becoming a core primitive for serious AI-assisted development. In this episode, Kaushik and Iury disambiguate "agent" terminology, unpack plan mode vs subagents, and explain how parallel, scoped workers improve research quality without polluting the main thread. Full shownotes at https://fragmentedpodcast.com/episodes/305
E304 · 9 Feb 2026 · 27 min
Agent Skills look simple, but they are one of the most powerful building blocks in modern AI coding workflows. In this episode, Kaushik and Iury break down when to use skills, how progressive disclosure works, and how skills compare with commands, instructions, and MCPs. Full shownotes at https://fragmentedpodcast.com/episodes/304
E303 · 2 Feb 2026 · 26 min
Ever get asked "how do LLMs work?" at a party and freeze? We walk through the full pipeline: tokenization, embeddings, inference — so you understand it well enough to explain it. Walk away with a mental model that you can use for your next dinner party.
E302 · 26 Jan 2026 · 19 min
MCPs are everywhere, but are they worth the token cost? We break down what Model Context Protocol actually is, how it differs from just using CLIs, the tradeoffs you should know about, and when MCPs actually make sense for your workflow. Full shownotes at https://fragmentedpodcast.com/episodes/302
E301 · 19 Jan 2026 · 25 min
Most folks reference "AI coding" like it's one thing. It's really not. In this foundational episode Kaushik & Iury walk through (at least) four paradigms — from super autocomplete to agent orchestration — each with different workflows, expectations, and mental models. What do most developers follow today? Where is the frontier? What's coming in the future? Listen to the episode and find out!
E300 · 12 Jan 2026 · 9 min
Fragmented is changing. New direction, new cohost. Kaushik explains the pivot from Android to AI development and introduces Iury Souza. From vibe coding to software engineering — one episode at a time.
E257 · 4 Mar 2025 · 48 min
Join us as we talk with Vinay Gaba, Android GDE and leading voice in Android development, about the future of the field. Vinay shares insights from interviews with top Android devs on their three-year predictions, and offers his own perspective. We cover AI's impact, evolving development roles, and crucial future skills. You can find the [full shownotes over at fragmentedpodcast.com](https://fragmentedpodcast.com/episodes/257).
E256 · 24 Feb 2025 · 22 min
In this episode, we talk about the art of rapid prototyping across various platforms and using Kotlin tech to get it done. Also, how will AI change this? Listen to find out more. You can find the [full shownotes over at fragmentedpodcast.com](https://fragmentedpodcast.com/episodes/256/).
E255 · 18 Feb 2025 · 32 min
In this episode, we dive into the programming paradigm — Data Oriented Programming (DOP) and why making data the star can simplify your code. Learn how well-modeled data reduces defensive logic, prevents invalid states, and keeps your apps stable. We’ll also contrast DOP with Object Oriented Programming (OOP) and Functional Programming (FP), sharing practical examples, tips, and resource links to deepen your understanding. The [full shownotes with illustrations are on fragmentedpodcast.com](https://fragmentedpodcast.com/episodes/255/).
E254 · 24 Dec 2024 · 49 min
In this episode, discover how Dan Rusu’s pods4k Immutable Arrays library can deliver 2–8× speed boosts and 5× lower memory usage in Kotlin/Android apps. We first revisit the fundamentals of autoboxing/unboxing and immutability to understand their impact on performance. Then we hear from Dan himself on his library, motiviations for building it, how the benchmarks were calculated and much much more. Our grand finale episode for 2024. Hope you enjoy it! Full Shownotes at https://fragmentedpodcast.com/episodes/254.
E253 · 10 Dec 2024 · 41 min
Kaushik looks at a new logging library from Square called logcat. He starts by seeing how the popular Timber library does it along with the benefits. He then interviews Pierre-Yves Ricau (Piwai) of Square, the creator of logcat, to explore its origins and advantages. Shownotes: https://fragmentedpodcast.com/episodes/253
E252 · 26 Nov 2024 · 25 min
In this episode of Fragmented, Kaushik dives into the importance of creating your own starter template to streamline app development and minimize decision fatigue. He shares insights from his own starter template - Playground Android. Looking to the future, JetBrains has an exciting tool called Amper that might make all of this much easier. Kaushik chats with JetBrains’ Márton Braun about Amper, an exciting new tool that could revolutionize Kotlin & Android project setups. Tune in to learn how to go from idea to code with less friction! You can find the full shownotes at…
E251 · 12 Nov 2024 · 18 min
In this episode, Kaushik explores the evolution of dependency injection (DI) in Android development. Dagger has been the de-facto solution for DI in Android but there might be a new king in DI-town. He also chats with friend of the show and dependency injection expert Ralf Wondratschek for a final gut check. Shownotes: https://fragmentedpodcast.com/episodes/251
E250 · 29 Oct 2024 · 34 min
We're back from the hiatus with our SemiQuicentennial episode! With the momentous 250 comes some big announcements and a shift in the way we do things. Listen to find out the details!
E249 · 10 Jul 2023 · 55 min
In this episode, Michael Bailey helps us explore the complexities of Java versions in the Android ecosystem, discussing JDK, JRE, Android Studio settings, Android app settings like compileSdk vs minSdk vs targetSdk, and concludes by providing resources for further learning.
E248 · 26 Jun 2023 · 1 hr 6 min
In this Fragmented podcast episode, host Donn Felker invites Ishan Khanna for an in-depth discussion about feature flags and A/B testing. They delve into the benefits, implementation strategies, best practices, and available tools, offering listeners valuable insights and resources to enhance their understanding of these critical development techniques.
E247 · 12 Jun 2023 · 1 hr 6 min
In this episode, we talk to, Siggi Jonsson. Siggi helps guide us through the complex and often confusing world of Android app modularization.
E246 · 29 May 2023 · 56 min
In this podcast episode, we have the pleasure to host Fred Porciúncula, a Google Developer Expert (GDE) known for his work with Kotlin Inject and his invaluable contributions to the Android development community. Fred offers his expertise on Dependency Injection (DI), Kotlin Multiplatform (KMP), and how they intersect.
E245 · 15 May 2023 · 55 min
In this episode, Donn and Kaushik talk to an old friend of the show, Colin White, about Treehouse, a combination of the Redwood and Zipline libraries.
E244 · 10 May 2023 · 10 min
In this episode, Donn and Kaushik announce that they are steering the podcast back into Android waters. In other words, the Fragmented Podcast is returning to its roots ... we're back to being a 100% Android Development focused show.
E243 · 10 Apr 2023 · 48 min
In this episode, Donn and Kaushik talk to long-time friend Dan Lew about his recent career switch from Android developer to TypeScript/Node.js/Progressive Web App Developer and what he learned.
E242 · 20 Mar 2023 · 40 min
In this episode, Donn and Kaushik talk about one of the age old bike shedding topics - code formatting, and how you can solve it with automation and tools.
E241 · 10 Jan 2023 · 45 min
In this episode, Donn and Kaushik talk about the fear of shipping, some impostor syndrome and how it contributes to uncertainty and doubt in your capabilities as a software developer.
E240 · 15 Dec 2022 · 55 min
In this episode, Donn and Kaushik talk about 5 new-ish Kotlin constructs that you might not be aware of.
Fragmented is an AI developer podcast for engineers who want to go beyond vibe coding and ship real software. We cover AI-assisted development the way working engineers actually use it: prompting strategies, code review, testing, debugging, workflows, and building production-grade software with AI tools. No hype. No "I shipped a SaaS in a weekend" stories. Just tactics that work. Hosted by Kaushik Gopal and Iury Souza — software engineers using AI daily to build and ship real products. From vibe coding to software engineering — one episode at a time. Our goal: help you use AI to become a better engineer, not be replaced by one.
Fragmented - AI Developer Podcast is a English tech & science podcast from Kaushik Gopal, Iury Souza. Melo plays each episode straight from the publisher's own feed — no ads added, no account needed — and remembers where you stopped, in this browser only.
The Melo app keeps playing with the screen off, works in the car and on your watch, wakes you to your station, and browses the whole catalogue offline. Free, no ads, no account.
