Loading post…
NotionAkshay KothariAnnouncement
Introducing Notion 3.0
Summary
Notion 3.0 introduces Notion AI Agents that can create documents, build databases, search across tools, and execute multi-step workflows inside a workspace. Agents can perform up to 20 minutes of autonomous work across hundreds of pages, including researching information, synthesising findings, creating structured databases, and notifying users when tasks finish. Users can personalise an Agent through a Notion page containing instructions and context, including task triage, response formatting, and reference information; templates can add specialised skills. The launch also includes database row permissions, new AI connectors, and additional MCP integrations, while Custom Agents are planned to run on schedules or triggers and share workflows with teams.
Context
The announcement addresses the time spent on busywork and the difficulty of using AI agents when work is scattered across rigid tools. It presents collaboration, access to work context, and the ability to take action as requirements for handling real knowledge-work workflows.
Approach / What changed
Notion 3.0 teaches Notion AI to use the platform’s documents, databases, and integrations to complete multi-step tasks. Users provide instructions and context through a Notion page, while future Custom Agents will run specialised workflows on schedules or triggers and can be shared with teams.
Takeaways
An Agent can work across Slack, Notion, and email to compile customer feedback, synthesise findings, create a structured database, and notify the user when finished.
Personalisation uses a Notion page as an editable memory bank for behavioural instructions, task triage, response formatting, and reference information.
Custom Agents are planned as specialised, shareable agents that run on schedules or triggers, including workflows for feedback, project updates, and IT requests.
Source and freshness
- Source
- notion.com
- Published
- Added to Yomu
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.