Notion has introduced a new developer platform designed to expand the capabilities of its AI agents, allowing customers to build automated workflows, connect external AI systems, deploy custom code, and synchronize data from third-party databases directly into Notion workspaces.
The announcement was made during a livestreamed product event on Wednesday. The productivity software company, widely known for its collaborative note-taking platform, said the new system is intended to turn Notion into a centralized workspace where human teams and AI agents can operate together across different tools and data sources.
The launch adds an orchestration layer to Notion’s platform, allowing AI tasks to coordinate across databases, applications, and external services. The company is positioning the platform as more than a productivity application with AI features, instead presenting it as infrastructure for managing workflows and agent-based automation.
Notion Expands Capabilities Of Custom AI Agents
Notion first introduced its Custom Agents in February. The AI tools were designed to handle repetitive workplace tasks such as answering common questions, preparing status updates, and automating routine workflows.
According to the company, customers have created more than 1 million agents since the feature launched.
However, the initial version of the agents had several technical limitations. They could not connect directly to external data sources or execute custom logic. Companies using outside AI agents also could not integrate those systems directly with their Notion environments.
As a result, teams often relied on third-party automation services or developed their own infrastructure and scripts to bridge those gaps.
“It’s true that, historically, Notion hasn’t been the most developer-focused platform,” said Ivan Zhao, Notion co-founder and chief executive officer, during the livestream. “But things are changing.”
Workers Feature Allows Custom Code Deployment
A central part of the launch is Workers, a cloud-based execution environment that allows customers to deploy custom code inside secure isolated sandboxes.
With Workers, developers can write custom logic, synchronize external data into Notion, create custom tools, and trigger automated actions through webhooks. Webhooks are automated signals that activate tasks when events occur in connected applications.
The company said customers will not necessarily need to write the code manually because AI coding agents can generate the required code.
Workers uses the same credit system already attached to Notion’s Custom Agents. However, the company said access will remain free through August to allow developers to test the system.
Platform Connects External Databases And AI Agents
The platform also introduces database synchronization tools powered by Workers. The feature allows Notion databases to pull and continuously update information from external systems that provide APIs.
The company said supported data sources can include services such as Salesforce, Zendesk, PostgreSQL, and other database platforms.
Zhao said the feature allows users to “use your Notion database as a sheer canvas to power both your workflows and your agents.”
Workers can also create agent tools that use custom logic in cases where MCP integrations are insufficient. MCP, short for Model Context Protocol, is an emerging standard designed to allow AI systems to connect with external software tools and data services.
Notion additionally introduced support for interacting directly with external AI agents from inside the workspace. Users can assign work to those agents, communicate with them, and monitor progress similarly to how they manage Notion’s own agents.
At launch, Notion said supported partner agents include Claude Code, Cursor, Codex, and Decagon. The company said more integrations are planned.
An External Agent API is also available for organizations that want to connect internally developed AI agents to Notion.
Notion Positions Platform As Workflow Infrastructure
Developers and AI agents access the platform through the Notion CLI, a command-line interface tool available across all company subscription plans.
The release marks a broader strategic shift for Notion as it expands from a productivity application into a programmable workflow platform. The company is entering a market increasingly focused on automating knowledge work and coordinating AI systems across business operations.
The launch also aligns with a wider movement across the AI industry, where companies are extending beyond chatbot products into systems capable of carrying out tasks across multiple software environments.
“Any data, any tool, any agent — that’s the big picture for the Notion Developer Platform,” Zhao said.
Featured image credits: Outsourced Staff
For more stories like it, click the +Follow button at the top of this page to follow us.