Notion just turned its workspace into a hub for AI agents

Productivity software maker Concept enters the age of agents.

In a live stream product announcement On Wednesday, the company, best known for its collaborative note-taking app, introduced a new developer platform that extends the capabilities of its custom AI agents, connects to remote agents and allows teams to build automated multi-step workflows that can pull data from any database.

By building an orchestration layer – a system that coordinates AI work across multiple tools and data sources – Notion is positioning itself as more than a note-taker with AI features and instead as a hub where people and agents can collaborate across tools and databases.

In February, Notion launched its first Custom agents — AI teammates that perform repetitive tasks such as answering frequently asked questions, compiling status updates, and automating workflows. Since then, Notion customers have built more than one million agents, the company says.

However, these resources had limitations. They couldn’t connect to external data or use custom logic. Remote agents that companies used also had no way to connect to the Notion workspace. Teams had to work around these issues by using third-party automation platforms or writing their own scripts that run on their own infrastructure.

“It is true that Notion historically has not been the most developer-focused platform,” said Ivan Zhao, co-founder and CEO of Notion, during the livestream. “But things are changing.”

Now Notion will allow teams to deploy their own custom code. With the new Workers, Notion’s cloud-based environment for running custom code, customers can write their logic and deploy it in a secure sandbox (an isolated environment that prevents code from interfering with other systems). This allows teams to do things like sync their data with Notion, build custom tools, and trigger work with webhooks – which are automated signals that trigger actions when something happens in another app – without having to rely on external infrastructure.

You don’t even have to write the code. The company points out that your favorite AI encryption agent can do this for you.

The Workers will use the same credit system as Custom Agents, but Notion is making this free through August so developers can experiment.

Syncing external data sources is also part of the Notion Developer Platform. The database sync feature, powered by Workers, can retrieve data from any database with an API. That means you can access data from places like Salesforce, Zendesk, Postgres, and others within your own Notion databases – and keep the data fresh.

Zhao noted that this means Notion’s users can now “use your Notion database as a canvas to power both your workflows and your agents.”

Employees can also build agent tools with custom logic, for those times when connecting to a third party via MCP – short for Model Context Protocol, an emerging standard that allows AI tools to connect to external data and services – isn’t enough.

Another addition allows Notion’s users to chat directly with third-party AI agents they use, assign them work, and track their progress, as if they were one of Notion’s own custom agents. At launch, Notion says Claude Code, Cursor, Codex, and Decagon are supported partner agents, but it plans to add more.

There’s also an External Agent API if teams want to connect their own internal agents to Notion, such as the ones they built specifically for their company’s needs.

Developers and agents interact with Notion’s new developer platform via the Understanding CLIa command-line tool for developers, available in the company’s Business and Enterprise plans.

The Developer Platform represents a shift in Notion’s strategy as it becomes more of a programmable platform than just an application, allowing it to compete with other workflow automation platforms. As companies increasingly look to automate their knowledge work and build internal AI systems, a platform that connects agents, custom code, and live data in one place is starting to look less like a productivity app and more like core infrastructure.

It also follows the broader trend among AI companies, which have gone beyond the AI ​​chatbot and offered agentic tools that can take actions across different software platforms.

“Every data, every tool, every agent – ​​that’s the big picture for the Notion Developer Platform,” Zhao said.