Notion just turned its workspace into a hub for AI agents
Notion has launched a new developer platform, transforming its workspace into a hub for AI agents. This platform allows custom AI agents to connect with external data and agents, enabling automated multi-step workflows. Notion aims to become a central hub for human and AI collaboration, moving beyond its traditional role as a note-taking application.
Notion has introduced a new developer platform, transforming its workspace into a central hub for AI agents and collaborative workflows. This initiative builds on its existing custom AI agents, which have seen over a million deployments since their February launch, and aims to provide more robust integration and automation capabilities. The company is positioning itself as an orchestration layer, coordinating AI work across various tools and data sources.
Previously, Notion's custom agents faced limitations regarding external data connectivity and custom logic. Teams often resorted to third-party platforms or custom scripts to bridge these gaps. The new platform addresses these challenges by allowing users to deploy their own custom code through Notion Workers, a cloud-based environment for secure code execution. This enables seamless data synchronization from external databases like Salesforce and Zendesk, and the creation of custom tools without external infrastructure.
The platform also facilitates interaction with external AI agents. Users can now chat directly with their preferred AI agents, assign tasks, and monitor progress within Notion. Supported partner agents include Claude Code, Cursor, Codex, and Decagon, with more planned for the future. An External Agent API is also available for companies to integrate their proprietary internal agents.
Notion's Developer Platform signifies a strategic shift from a mere application to a programmable platform. This move positions Notion to compete with other workflow automation platforms, catering to the growing demand for automated knowledge work and internal AI systems. By consolidating agents, custom code, and live data, Notion is evolving into a core infrastructure solution rather than just a productivity app.
Related articles
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
CUGA, IBM's open-source Agent Harness, simplifies building agentic applications by handling infrastructure, allowing developers to focus on tools and prompts. It offers pre-assembled components for planning, execution, and state management, significantly reducing development time. CUGA has topped agent benchmarks like AppWorld and WebArena.
OpenAI launches new initiative to help find and patch open source bugs
OpenAI has launched "Patch the Planet," a new initiative in partnership with cybersecurity firm Trail of Bits, to enhance the security of open-source projects. This program aims to assist maintainers in identifying and patching bugs, utilizing OpenAI's AI-powered security tools while reducing the burden on project teams.
PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters
Baidu has released PP-OCRv6, an advanced optical character recognition (OCR) model supporting 50 languages. Available on Hugging Face, this version significantly improves accuracy and efficiency across various parameter sizes, from 1.5 million to 34.5 million, marking a substantial leap in multilingual OCR technology.
