5 quotes from 1 episode on How I AI, each with a timestamped link to the source.
5 quotes1 episode
The short version
Ryan Nystrom states AI agents require software engineers to act as systems architects. A custom agent generated a complete feature and submitted a pull request with a preview link in 20 minutes.
Most interesting insights
Software engineers act as systems thinkers who build verification loops to check the correctness of automated code changes.
“I view our job as like engineers evolving into like systems thinkers and architects and not and not even just necessarily writing like the spec and thinking about the behaviors but most importantly is like the verification loop like is it a like how should it verify correctness of this feature um or this change.”
Automated meeting summaries eliminate preparation time and let teams review generated updates right as a call starts.
“I can basically work up until like the minute of our meeting without having done a bunch of like prep. And then we all get on a video call and we look at this screen and we're like, 'Okay, here's what we need to talk about.'”
An internal agent built a tab block feature in under 20 minutes. The system provided a pull request link and a preview environment for the entire implementation.
“A friend of mine, um who's a notion fan text me. He's like, 'Hey, I like the tab block that you built.'”
“10:40 10:51 started the implementation and then another 10 minutes later it replies with a pull request link and a preview URL because we like we do the um like preview environment stuff and it like built the entire thing.”
“If I've got a CI loop that takes an hour to run, that, your agent's just going to sit there and spin for like an hour waiting for results to like do something. If it takes three minutes to run, like holy crap, how much more stuff are you you as a human and then especially as your like little swarm of agents going to be able to get done?”
Automate Low-Value Prep: Notion's "Hot Potato" AI agent autonomously gathers updates from Slack, tasks, and pull requests, generating a meeting pre-read daily at 9:00 a.m.
Shift Meeting Focus: By eliminating rote status updates, teams can dedicate standup time to discussing problems, making decisions, and celebrating wins, as Nystrom describes.
Notion’s internal “Boxy” system integrates an AI agent called Codeex to automate code generation and bug fixes directly from Notion tasks.
Engineers describe a task with natural language and a screenshot, @mention Codeex, and the AI produces a complete pull request with UI verification and a preview URL.
Notion's engineers, led by Ryan Nystrom, are ditching traditional code-first development for a spec-driven approach. They start with comprehensive, plain English markdown documents, not a single line of code.
AI agents like Whisper (for dictation) and Codeex (for spec generation and code building) form the backbone of this system. Nystrom "yapped" a feature idea into Whisper, then fed it to Codeex to create the spec.
Your engineering team's comfort making frequent changes directly links to CI speed; slow CI creates “monster changes” no one wants to review.
AI agents supercharge this effect: they generate changes around the clock, amplifying the bottleneck of a slow Continuous Integration pipeline exponentially.
How we attribute quotes. Every quote was matched against the episode transcript, so the words and the timestamp are real (we trim filler words like "um", nothing else). The name comes from our written summary of the episode. YouTube gives us no voice-by-voice transcript, so open the timestamp to hear who is talking. See a wrong name? Tell us and we fix or remove it.