Notion Introduces Developer Platform for AI Agents and Custom Workflows

May 14, 2026
Notion has launched a new Developer Platform that allows users to create and connect AI agents, sync external data, and deploy custom code within its workspace. The update includes Workers for running code in a secure environment, an External Agent API, and support for agents like Claude Code and Codex.

Notion has introduced a new Developer Platform that turns its workspace into a hub for AI agents, announced on its website. The platform allows teams to build and connect AI agents, automate workflows, and integrate external data sources within Notion.

The platform's key component, called Workers, enables users to deploy custom code in a secure hosted environment. Teams can use Workers to synchronize data from external databases such as Salesforce, Zendesk, and Postgres, or to build tools that trigger actions through webhooks. Notion is making the Workers feature free to use through August.

The update also introduces an External Agent API that lets companies connect their own internal agents to Notion. Supported partner agents at launch include Claude Code, Cursor, Codex, and Decagon. Users can interact with these agents directly, assign tasks, and monitor their progress within the same workspace.

Developers can access these capabilities through the Notion Command Line Interface, available on Business and Enterprise plans. The new platform expands Notion's role beyond note taking by providing a programmable environment where people and AI agents can collaborate across tools and data systems.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.