NO
Use cases / Getting started
Notion Bot
One Notion page per task, with notes, then a cloud session when it needs hands.
Author names, descriptions and prompts are preserved as published. Need a starting point? Read the bot selection guide →
The story behind this use case
Brian Lovin's multi-tasking pattern is two steps. First, tell your agent to keep all work organized in a Notion database and take detailed notes about progress and blockers on each page. Second, throw tasks into chat — manually, or automatically pulled from email, Sentry, or GitHub with routines — and most of the time those init a Cursor cloud session that starts building or fixing.
It's the best way he's found for one bot to work on many things at once while keeping visibility into what's flowing through the system, and the best way to resume an old task that got buried in a chat thread: ask the bot to find the right Notion page and get caught up. With the Notion MCP you don't do the setup by hand. Notion's own account quote-tweeted it.
Screenshots & demos
Prompt
This reference prompt was supplied by its author. Review it before giving it to your agent.
Using the Notion MCP, build me this system: a Notion database where you keep every task you're working on, one page each, with detailed running notes on progress and blockers. When I drop a task in chat (or a routine pulls one from email/Sentry/GitHub), create the page and kick off a Cursor cloud session to start on it. When I ask about an old task, find its page and catch me up on progress and next steps.