195: Going on-call 🚨

195: Going on-call 🚨

Author: Kaushik Gopal, Iury Souza April 20, 2020 Duration: 53:38
Have you ever gone on on-call rotations for your company? What is on-call? How to operate a successful on-call strategy? What does on-call for mobile mean? What are some tools and resources to help with on-call rotations? In this episode Donn and Kaushik dive into these topics.

Tired of the endless hype cycle around artificial intelligence in software development? Fragmented-AI Developer Podcast cuts through the noise for engineers who are focused on building and shipping reliable systems. Hosts Kaushik Gopal and Iury Souza, both working software engineers, steer conversations toward the practical, often unglamorous, integration of AI tools into real development workflows. In each episode, you’ll hear detailed discussions on effective prompting strategies that go beyond basic examples, methods for incorporating AI into rigorous code review and testing processes, and debugging the often-unpredictable output of these models. This podcast is grounded in the reality of building production-grade software, deliberately avoiding superficial success stories in favor of sustainable tactics. The focus remains on how AI-assisted development can genuinely augment an engineer’s daily work-from refining a personal workflow to architecting more robust systems. If you’re looking for actionable insights that translate directly to your codebase, this is the podcast for you.
Author: Language: en-us Episodes: 100

Fragmented - AI Developer Podcast
Podcast Episodes
310 - Mitchell Hashimoto on Ghostty & His Agentic Coding Workflow [not-audio_url] [/not-audio_url]

Duration: 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…
309 - Background Agents [not-audio_url] [/not-audio_url]

Duration: 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…
308 - How Image Diffusion Models Work - the 20 minute explainer [not-audio_url] [/not-audio_url]

Duration: 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 actual…
307 - Harness Engineering - the hard part of AI coding [not-audio_url] [/not-audio_url]

Duration: 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…
306 - Keeping your agent instructions in sync and effective [not-audio_url] [/not-audio_url]

Duration: 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, compar…
305 - Subagents explained - What they are, when (not) to spawn them [not-audio_url] [/not-audio_url]

Duration: 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 imp…
304 - Agent Skills - when to use them and why they matter [not-audio_url] [/not-audio_url]

Duration: 26:47
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 sk…
303 - How LLMs Work - the 20 minute explainer [not-audio_url] [/not-audio_url]

Duration: 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 ca…
302 - MCPs Explained - what they are and when to use them [not-audio_url] [/not-audio_url]

Duration: 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 f…
301 - The AI coding ladder [not-audio_url] [/not-audio_url]

Duration: 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 diffe…