At the “Make with Notion” event on Thursday, the company announced the launch of its first AI agent. This agent will use all of a user’s Notion pages and databases as context to automatically generate notes and analysis for meetings, competitor evaluation reports, and feedback landing pages.
The productivity platform stated that the agent can create new pages and databases or update existing ones with new data, properties, or views. Users can also trigger Notion agents from outside platforms that are linked to the service. For example, you can ask the Notion agent to create a bug tracking dashboard by pulling information from various sources like Slack, email, and Google Drive.
This newly announced Agent builds upon Notion AI, a pre-existing feature that could search or summarize content. However, the new agent is capable of tackling more complex multi-step tasks by utilizing the power of agentic AI. The company said the current version of the agent can perform a task that runs for up to twenty minutes across hundreds of pages.
Users can set up a profile page for the agent to instruct it on how to reference sources, define an output style, and specify where to update tasks and final results. You will also be able to ask the agent to remember key points as people use it. Those memories will be stored on the profile page, where users can review and edit them.
In demo videos, the company provided examples of agents that could offer feedback for landing pages and update them, create a restaurant tracker, generate an analysis from meeting notes, and prepare a competition analysis report.
Currently, these actions must be triggered manually. But Notion said the ability to create customized agents that work on a schedule or from specific triggers is coming soon. The company will also release a template library for agents, allowing users to pick ready-made prompts suited to their tasks.
Over the last two years, Notion has released a calendar app, a Gmail client, a meeting notetaker, and an enterprise search tool to get information from different sources. These features provided the company with the contextual building blocks necessary to create these automations. Other enterprise knowledge and productivity platforms, including Salesforce, Fireflies, and Read AI, have also launched their own agents to extract and update information.