Skip to content
How I AIHow I AI

Never write an update again: Notion's AI-powered engineering meetings | Ryan Nystrom

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: https://workos.com?utm_source=lennys_howiai&utm_medium=podcast&utm_campaign=q22025 Orkes—The enterprise platform for reliable applications and agentic workflows: https://www.orkes.io/ *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 *Blog & detailed workflow walkthroughs from this episode:* How I AI: Ryan Nystrom’s 3 Notion Workflows for Engineering Velocity: https://www.chatprd.ai/how-i-ai/ryan-nystrom-notion-workflows-for-engineering-velocity ↳ Implement Features Using Spec-First Development and an AI Coding Agent: https://www.chatprd.ai/how-i-ai/workflows/implement-features-using-spec-first-development-and-an-ai-coding-agent ↳ From Notion Task to GitHub Pull Request in 20 Minutes with a Coding Agent: https://www.chatprd.ai/how-i-ai/workflows/from-notion-task-to-github-pull-request-in-20-minutes-with-a-coding-agent ↳ Automate Daily Standup Preparation with a Custom Notion AI Agent: https://www.chatprd.ai/how-i-ai/workflows/automate-daily-standup-preparation-with-a-custom-notion-ai-agent *Tools referenced:* • Notion AI: https://www.notion.com/product/ai • Notion Custom Agents: https://www.notion.com/blog/introducing-custom-agents • Codex (OpenAI): https://openai.com/codex • Claude Code (Anthropic): https://claude.ai/code • Honeycomb (observability + MCP): https://www.honeycomb.io • Whisper (OpenAI voice transcription): https://openai.com/research/whisper • Slack: https://slack.com • GitHub: https://github.com *Other references:* • How Stripe built “minions”—AI coding agents that ship 1,300 PRs weekly from Slack reactions | Steve Kaliski (Stripe): https://www.chatprd.ai/how-i-ai/stripes-ai-minions-ship-1300-prs-weekly-from-a-slack-emoji • Notion 3.3 Custom Agents launch (February 24, 2026): https://www.notion.com/releases/2026-02-24 *Where to find Ryan Nystrom:* X: https://x.com/ryannystrom LinkedIn: https://www.linkedin.com/in/ryannystrom/ GitHub: https://github.com/rnystrom *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Ryan NystromguestClaire Vohost
May 11, 202647mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Notion’s AI agents streamline meetings, coding, and spec-driven development workflows

  1. Notion’s team replaces manual standup prep with a daily auto-generated pre-read that compiles Slack, tasks, PRs, metrics, and prior meeting context into an agenda-focused meeting doc.
  2. The workflow emphasizes high-frequency, high-quality meetings by removing update-theater and ensuring each engineer’s work is surfaced equally, improving engagement and reducing coordination risk.
  3. Notion built an internal “Boxy” system that lets engineers @mention Codex from Notion comments to run on background VMs, producing PRs, preview deploys, and self-testing artifacts quickly.
  4. The team is moving toward spec-first development where agent-readable markdown specs live in the repo, drive implementation, and act as a versioned source of truth for feature behavior and verification.
  5. Ryan argues AI changes engineering roles toward system design and verification loops, making fast CI and strong DevEx critical because agents scale output but are bottlenecked by slow feedback cycles.

IDEAS WORTH REMEMBERING

5 ideas

Automate context collection so meetings become decision-making, not reporting.

A custom Notion agent compiles the last 24 hours of Slack, closed tasks, merged PRs, metrics (e.g., Honeycomb), and yesterday’s transcript into a structured agenda, letting the team jump straight into problems, decisions, and risks.

High-frequency meetings work only when the prep cost is near zero.

Ryan and Claire argue that reducing meeting frequency is often a reaction to low-quality updates; rich auto-generated pre-reads enable daily alignment without the usual overhead.

Context surfacing “democratizes” visibility across personalities.

By automatically pulling concrete work artifacts, quieter engineers’ contributions show up alongside more vocal teammates, improving awareness and enabling better technical discussion.

Cutting meeting-prep toil is a practical burnout prevention lever.

Saving even ~20 minutes/day matters less for time and more for reducing context switching and “paperwork,” allowing managers and engineers to stay in creative, hands-on flow longer.

Engineering leaders should stay close to code because AI lowers the barrier.

Ryan’s stance is that line managers (and even senior leaders) can meaningfully contribute via small fixes, optimizations, and bug work—without needing to be the hero on the highest-risk projects.

WORDS WORTH SAVING

5 quotes

I've been in way too many meetings where I can tell, like, everybody's eyes are glazed over. Nobody's paying attention.

— Ryan Nystrom

I can basically work up until, like, the minute of our meeting without having done a bunch of, like, prep.

— Ryan Nystrom

It's not even just about, like, saving that 20 minutes, but it's, like, protecting my brain from, like, having to context shift about all this stuff.

— Ryan Nystrom

I, I kind of think that this is like the future of software engineering, where I then opened up Codex again, pointed it at this spec file, and I said, "Build it." And it basically one-shotted this.

— Ryan Nystrom

One of your human teammates. Be like, "No, man, look it up. It makes it..."

— Claire Vo

AI-generated standup pre-reads in NotionCustom agents with scoped permissionsSlack/GitHub/telemetry context aggregationHigh-frequency meetings vs. low-value status updatesBurnout reduction through less meeting prepBackground VM “Boxy” + @mention-to-PR workflowSpec-first development and verification tooling in-repo

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome