How Notion AI Changed Work at Notion
summary
Notion demonstrates that agents actually do work: employees build 836 custom agents (almost one per 1,000 people) that view websites and images, run scheduled triggers, edit databases, and execute multi‑step plans. An office bot called Smilers answers Slack questions, creates tickets in Notion, and updates the wiki, cutting roughly 10 hours/week from the environment team’s workload. Personal agents scrape an agenda into a database in minutes and a custom interview agent is prototyped in 3–4 minutes, then auto‑creates pages and fills summaries.
AI-written summary · about
chapters (10)
- 0:00Introduction and journey
- 3:29Personal agent power-ups
- 7:24Live demo begins
- 12:00Rusty’s database builder
- 16:55Luca’s shortcuts
- 20:52Ash’s automated briefings
- 21:34Smilers the environment agent
- 30:00Building a custom agent
- 35:40Three use cases to try
- 36:45Closing and call to action
related talks
31mFireside Chat
21mThe Agent Native Company
29mWhat exactly are AI Agents?
49mHow to be an AI First company
57mWhen AI Agent Teams Work (And When They Just Create More Work)
14mA New Way to Work: How We Made Our Team AI Native
49mAI agents won’t save your productivity– human–agent collaboration will
36mAI Agents in Automation | 3 Real Production Cases with ROI