Notion just turned its workspace into a hub for AI assistants

A software developer Thoughts going into the Agent’s time.

In the words of the living product announcement On Wednesday, the company, which is best known for its note-taking software, launched a new software development platform that expands the capabilities of its AI agents, connects with external agents, and allows teams to create multi-step automated systems that can pull data from any database.

By building an orchestration system – a system that integrates AI functions across multiple devices and data sources – Concept is positioning itself as more than just an AI editor and interface and instead as a place where people and agents can connect tools and databases.

In February, Notion launched its first Custom Agents – AI teammates who perform repetitive tasks, such as answering frequently asked questions, making behavioral changes, and improving workflows. Since then, Notion customers have created more than one million agents, the company says.

However, these delegates had limitations. They couldn’t connect to external data or use their own logic. The external agents that the companies used also did not have a way to connect to Notion’s working environment. Organizations have to solve these problems by using third-party platforms or writing their own scripts that run on their own architecture.

“It’s true that, historically, Notion has not been a very stable platform,” said Ivan Zhao, Notion co-founder and CEO, during the game. “But things are changing.”

Now, Notion will allow teams to use their own code. With its new Workforce, Notion’s cloud environment that runs code, customers can write their ideas and send them to a secure sandbox (a remote environment that prevents code from interfering with other systems). This allows teams to do things like sync their data in Notion, create new tools, and launch tasks with webhooks — which are automated signals that trigger an action when something happens in another app — without relying on external tools.

You don’t even have to write code. The company suggests that your AI assistant can do this for you.

Agents will use the same credit system as Custom Agents, but Notion is making it free until August, so developers can try it out.

Integrating external data sources is also part of the Notion Developer Platform. With the help of Workers, the database interface can pull data from any database with an API. This means you can get data from places like Salesforce, Zendesk, Postgres, and others into your Notion databases — and keep the data available.

Zhao added that this means that Notion users can now “use your Notion database as a canvas to manage your projects and your agents.”

Operators can also create tools for agents with traditional logic, when communicating with a third party via MCP — short for Model Context Protocol, an emerging standard that allows AI tools to connect to external data and services — is not enough.

Another integration allows Notion users to interact directly with the external AI agents they use, assign them tasks, and monitor their progress, as if they were one of Notion’s agents. At launch, Notion says the Claude Code, Cursor, Codex, and Decagon are supporting players, but they want to add more.

There’s an External Helper API, too, if teams want to connect their internal helpers with Notion, such as those designed specifically for their company’s needs.

Developers and supporters connect to Notion’s New Developer Platform via CLI conceptsa line management tool for developers, available on Business and Enterprise Plans.

The Developer Platform represents a change in Notion’s strategy as it becomes a platform that is more than just an application, setting it up to compete with other application management platforms. As businesses focus on leveraging information and building internal AI systems, a platform that integrates agents, source code, and live data in one place is beginning to look more like a software product and more like an infrastructure.

It also follows the growing trend of AI companies, which have been moving beyond AI chatbots to provide technology tools that can interact across platforms.

“Every tool, every tool, every assistant – that’s the big picture of the Notion Developer Platform,” Zhao said.