How I AI
How I AI

Spec-driven development: The AI engineering workflow at Notion | Ryan Nystrom

May 11, 2026

AI Summary

5 min read

Ryan Nystrom, an engineering manager at Notion who manages a small team and writes code, shares how AI tools have reshaped his workflows. He demonstrates automating stand-ups, using background agents for code changes, and implementing spec-driven development in a large codebase, all while emphasizing faster CI as a prerequisite for agentic work.

Automating Stand-ups with Custom Agents

Nystrom's team runs daily stand-ups but eliminates manual prep through a Notion AI custom agent called "Hot Potato," triggered at 9 a.m. It scans the past 24 hours of Slack channels, closed Notion tasks, merged pull requests, Honeycomb metrics via MCP (managed compute provider), and the previous day's meeting transcript. The agent compiles a brief, fun pre-read in a standardized template covering CI speeds, decisions, progress, bugs, feedback, open questions, and risks. This populates a shared meeting page, which the team reviews on video calls.

The result is meetings focused on problems, wins, and next steps rather than rote updates. It surfaces details like a 13% test improvement from a mock server fix, prompting discussion. Nystrom notes this democratizes input from quieter team members and reduces context-switching tedium—saving about 20 minutes daily while protecting against burnout. Managers can code until the meeting starts, as the agent handles synthesis without complaint.

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

What you'll learn

  • 1 (00:04) **Intro Banter on AI Workflows** - Ryan shares rapid spec-to-code process using Whisper, Codex, and Markdown.
  • 2 (01:13) **Episode Intro and Project Overview** - Claire introduces Ryan's Notion AI demos for stand-ups, background agents, and spec-driven dev.
  • 3 (02:49) **AI's Impact on Daily Work** - Ryan describes upending 12+ years of routines with frequent tool changes.
  • 4 (04:30) **Team Management with Notion AI** - Manages 6-7 engineers on fast AI-pilled projects like CI optimization.
  • 5 (06:42) **Automated Daily Stand-Ups** - Custom agent generates pre-reads from Slack, tasks, PRs, transcripts, metrics.
  • 6 (08:50) **High-Quality Meeting Benefits** - Detailed pre-reads spark discussions, surface hidden wins like 13% test improvements.
  • 7 (10:57) **Reducing Burnout via Automations** - Frees time from prep, lets managers code until meetings start.

+ Full timestamped outline available in the app

Show Notes

Ryan Nystrom is a software engineer at Notion. He joined in December 2024 after Notion acquired Campsite, the team communication platform he co-founded with Brian Lovin. At Notion, he’s been a core builder of Notion AI and the Custom Agents feature launched in February 2026. He manages a team of six to seven engineers while still writing code himself, currently running Project Afterburner, a push to cut Notion’s CI time to a quarter of its current duration.


What you’ll learn:

  1. How to build a Notion AI custom agent that auto-generates your daily standup pre-read by pulling from Slack, GitHub, Honeycomb metrics, and yesterday’s meeting transcript
  2. How to configure subagents and MCP integrations within Notion AI
  3. How Notion’s internal “Boxy” system lets engineers @mention Codex from within Notion comments and get a full pull request with screenshots in 20 minutes
  4. The spec-first development workflow: dictate an idea into Whisper, have Codex format it as a proper spec, commit it to the repo, and let the agent implement and verify it autonomously
  5. Why fast CI is absolutely critical in the age of AI coding agents
  6. How to prompt AI coding agents to defend their reasoning under pushback
  7. Why engineering managers and even senior executives should keep writing code

Brought to you by:

WorkOS—Make your app enterprise-ready today

Orkes—The enterprise platform for reliable applications and agentic workflows

In this episode, we cover:

(00:00) Introduction to Ryan Nystrom

(02:48) How AI has upended 12+ years of the same working routine

(04:30) Project Afterburner: Notion’s push to cut CI time to a quarter

(09:00) Why high-frequency, high-quality meetings beat lower-frequency standups

(11:10) How automated context surfaces every engineer’s work equally

(12:15) Why cutting meeting prep is a burnout protection mechanism

(14:26) The case for engineering managers writing code

(16:13) Inside “Boxy”: Notion’s internal VM-based background agent system

(20:30) Old World vs. New World code review

(24:51) Prompting Codex from Notion comments

(29:20) The emotions around code review

(31:01) Quick recap

(32:00) Spec-first development: writing and checking agent specs into the repo

(35:10) The spec as changelog: version control for how a feature actually works

(37:53) How engineers’ roles are evolving

(39:00) Lightning round

(45:21) Where to find Ryan

Tools referenced:

• Notion AI: https://www.notion.com/product/ai

• Notion Custom Agents: <

How I AI

More from this podcast

How I AI →