Home Podcasts Fragmented - AI Developer Podcast
Fragmented - AI Developer Podcast

Fragmented - AI Developer Podcast

Kaushik Gopal, Iury Souza 270 Episodes Sep 6, 2026

Fragmented is a podcast for software engineers who want to use AI in real development work beyond casual vibe coding. It covers prompting, code review, testing, debugging, workflows, and building production-grade software with AI tools. Hosts Kaushik Gopal and Iury Souza share practical tactics from their experience as engineers using AI daily. The show focuses on helping engineers become better at their craft with AI rather than being replaced by it.

Episodes

311 - Self learning harnesses are here
311 - Self learning harnesses are here Sep 6, 2026 00:12:41 Claude Code and Codex have been the mainstay agent harnesses, with OpenCode and Pi as the popular open-source alternatives. But two new entries are pushing what a harness even is: DeepSeek's Cordis kernel, where everything — down to the agent loop itself — is a plugin you can hot-swap at runtime, and Prime Agent, an RLM-based harness that treats sub-agents and context as function calls in a live R
310 - Mitchell Hashimoto on Ghostty & His Agentic Coding Workflow
310 - Mitchell Hashimoto on Ghostty & His Agentic Coding Workflow Apr 14, 2026 00:59:43 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
309 - Background Agents
309 - Background Agents Apr 1, 2026 00:25:37 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 fir
308 - How Image Diffusion Models Work - the 20 minute explainer
308 - How Image Diffusion Models Work - the 20 minute explainer Mar 24, 2026 00:24:44 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 fragmentedpodcast.com. Show Notes Episode 303 - How LLMs work in 20 minutes -
307 - Harness Engineering - the hard part of AI coding
307 - Harness Engineering - the hard part of AI coding Mar 17, 2026 00:29:55 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 fragmentedpodcast.com. Show Notes Why it matters Harness Engineering - OpenAI's post on building their Codex c
306 - Keeping your agent instructions in sync and effective
306 - Keeping your agent instructions in sync and effective Mar 10, 2026 00:23:22 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 fragmentedpodcast.com. Show Notes The sync problem AGENTS.md - Official spec
305 - Subagents explained - What they are, when (not) to spawn them
305 - Subagents explained - What they are, when (not) to spawn them Feb 17, 2026 00:26:38 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 fragmentedpodcast.com.Show NotesResources & DocumentationOfficial DocumentationAgents, Modes, Subagents: o
304 - Agent Skills - when to use them and why they matter
304 - Agent Skills - when to use them and why they matter Feb 9, 2026 00:26:47 Agent Skills look simple, but they are one of the most powerful building blocksin modern AI coding workflows. In this episode, Kaushik and Iury break down whento use skills, how progressive disclosure works, and how skills compare withcommands, instructions, and MCPs.Full shownotes at fragmentedpodcast.com.Show NotesMain ReferencesProgressive Disclosure -how skills are loaded into contextAgent Ski
303 - How LLMs Work - the 20 minute explainer
303 - How LLMs Work - the 20 minute explainer Feb 2, 2026 00:25:45 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._Full shownotes at fragmentedpodcast.com.Show NotesWords -> Tokens:OpenAI Tokenizer visualizer -Visualize how text becomes tokensTokens -> Embeddin
302 - MCPs Explained - what they are and when to use them
302 - MCPs Explained - what they are and when to use them Jan 26, 2026 00:19:09 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 fragmentedpodcast.com/episodes/302.Show NotesMCP - Model Context ProtocolRemote MCP server example - GleanAAIF -Agentic AI Foundation setup by Li
301 - The AI coding ladder
301 - The AI coding ladder Jan 19, 2026 00:24:38 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!Full sho
300 - From Vibe coding to Software engineering
300 - From Vibe coding to Software engineering Jan 12, 2026 00:08:44 Fragmented is changing. New direction, new cohost. Kaushik explains the pivotfrom Android to AI development and introduces Iury Souza.From vibe coding to software engineering — one episode at a time.Full shownotes at fragmentedpodcast.com.Contact usNewsletterWebsiteContact usYoutubeCo-hosts:Kaushik GopalIury Souza

Recommended