Stream the latest episode
Listen and watch now on YouTube, Spotify, and Apple. See the episode transcript at the top of this page, and timestamps for the episode at the bottom.
Brought to You by
• Statsig — The unified platform for flags, analytics, experiments, and more. Graphite is one example of a company that has built granular control and rapid iteration into their development workflow using Statsig. Read more about how Graphite uses Statsig and try it out.
• Linear – The system for modern product development. Vibe coding is having its moment: but what vibe coding doesn’t account for is institutional knowledge. Linear agents, on the other hand, work inside your team’s shared workspace. See how agents work in Linear and give Linear a go to try it yourself.
—
In this episode
Addy Osmani is Head of Chrome Developer Experience at Google, where he leads teams focused on improving performance, tooling, and the overall developer experience for building on the web. If you’ve ever opened Chrome’s Developer Tools bar, you’ve definitely used features Addy has built. He’s also the author of several books, including his latest, Beyond Vibe Coding, which explores how AI is changing software development.
In this episode of The Pragmatic Engineer, I sit down with Addy to discuss how AI is reshaping software engineering workflows, the tradeoffs between speed and quality, and why understanding generated code remains critical. We dive into his article The 70% Problem, which explains why AI tools accelerate development but struggle with the final 30% of software quality—and why this last 30% is tackled easily by software engineers who understand how the system actually works.
Jump to interesting parts
The 70% Problem (22:15)
Why you should keep expectations low, and control high when using AI coding tools (32:58)
How the engineering manager and product manager roles might be changing with these AI tools (42:49)
An interesting quote from this episode
How Addy uses AI tools for his own coding:
Gergely (at 06:14): “How do you personally use these AI tools?”
Addy: “I have more recently been focusing on the idea of spec-driven development, having a very clear plan of what it is that I want to build.
There are definitely places where I still vibe code. If it’s for a personal tool, something throw away, in the old days, if an engineer or a PM had an idea, maybe we would put together a quick mock, maybe we would put together a wireframe or a sketch or something like that. Perhaps work with UX to come up with something a little bit more polished.
I think that tests are great. And if you are open to tests, it can be a great way of de-risking your use of LLMs and coding. Because sometimes, even if you’re using state-of-the-art models, you can end up in a situation where maybe the code looks more convoluted than you would expect. Or maybe your first couple of prompts have been generating really good code, and then for whatever reason, things go off. the rails. But if you can prove that things are working with tests and that if something did go off the rails, it’s clearer to you what that was, I think that that can help you keep your project green the whole time.”
The Pragmatic Engineer deepdives relevant for this episode
Timestamps
(00:00) Intro
(02:17) Vibe coding vs. AI-assisted engineering
(06:07) How Addy uses AI tools
(13:10) Addy’s learnings about applying AI for development
(18:47) Addy’s favorite tools
(22:15) The 70% Problem
(28:15) Tactics for efficient LLM usage
(32:58) How AI tools evolved
(34:29) The case for keeping expectations low and control high
(38:05) Autonomous agents and working with them
(42:49) How the EM and PM role changes with AI
(47:14) The rise of new roles and shifts in developer education
(48:11) The importance of critical thinking when working with AI
(54:08) LLMs as a tool for learning
(1:03:50) Rapid questions
References
Where to find Addy Osmani:
• LinkedIn: https://www.linkedin.com/in/addyosmani
• Website: https://addyosmani.com
• Newsletter:
Mentions during the episode:
• Beyond Vibe Coding: From Coder to AI-Era Developer: https://www.amazon.com/Beyond-Vibe-Coding-AI-Era-Developer/dp/B0F6S5425Y
• Building large scale web apps: https://www.amazon.com/Building-large-scale-web-apps-ebook/dp/B0CZ9H2XN5
• Chrome DevTools (MCP) for your AI agent: https://developer.chrome.com/blog/chrome-devtools-mcp
• Mitchell Hashimoto on X: https://x.com/mitchellh
• Cline: https://cline.bot
• VS Code: https://code.visualstudio.com
• Cursor: https://cursor.com/
• Copilot: https://github.com/features/copilot
• The 70% problem: Hard truths about AI-assisted coding:
• How AI-assisted coding will change software engineering: hard truths: https://newsletter.pragmaticengineer.com/p/how-ai-will-change-software-engineering
• Python, Go, Rust, TypeScript and AI with Armin Ronacher: https://newsletter.pragmaticengineer.com/p/python-go-rust-typescript-and-ai
• DeepMind: https://deepmind.google
• Gemini: https://gemini.google.com
• Stackoverflow: https://stackoverflow.com
• Jules: https://jules.google
• CodeX: https://chatgpt.com/codex
• JavaScript: https://www.javascript.com
• Bolt: https://bolt.new
• Building Web Apps with Bolt: Unlock the Future of AI-First Development: https://www.amazon.com/Building-Web-Apps-Bolt-Development/dp/B0F6SP872Y
• The Software Engineer’s Guidebook: Navigating senior, tech lead, and staff engineer positions at tech companies and startups: https://www.amazon.com/dp/908338182X
• AI Engineering: Building Applications with Foundation Models: https://www.amazon.com/AI-Engineering-Building-Applications-Foundation/dp/1098166302
• AI Engineering with Chip Huyen: https://newsletter.pragmaticengineer.com/p/ai-engineering-with-chip-huyen
• The AI Engineering Stack: https://newsletter.pragmaticengineer.com/p/the-ai-engineering-stack
—
Production and marketing by Pen Name.
