惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Engineering at Meta
Engineering at Meta
G
Google Developers Blog
WordPress大学
WordPress大学
M
MIT News - Artificial intelligence
D
DataBreaches.Net
云风的 BLOG
云风的 BLOG
爱范儿
爱范儿
Microsoft Security Blog
Microsoft Security Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
H
Hackread – Cybersecurity News, Data Breaches, AI and More
Blog — PlanetScale
Blog — PlanetScale
T
Tailwind CSS Blog
S
SegmentFault 最新的问题
阮一峰的网络日志
阮一峰的网络日志
博客园 - 三生石上(FineUI控件)
酷 壳 – CoolShell
酷 壳 – CoolShell
Recent Announcements
Recent Announcements
T
The Blog of Author Tim Ferriss
I
InfoQ
MyScale Blog
MyScale Blog
V
V2EX
B
Blog
罗磊的独立博客
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More

InfoWorld

AWS boosts CloudWatch Logs query limits by 10x to ease debugging for developers, SREs 21 LLMs tuned for special domains The new AI lock-in AWS adds Advanced Prompt Optimization tool to Bedrock Capacity markets could reshape cloud computing Four cutting-edge tools for spec-driven development Anthropic puts Claude agents on a meter across its subscriptions Using continuous purple teaming to protect fast-paced enterprise environments A better way to work with SQL Server Evidence-driven workflows: Rethinking enterprise process design AWS debuts Graviton-powered Redshift RG instances to cut analytics costs SAP’s AI promises last year? Most are still rolling out First look: Lemonade serves up local AI with limitations GitLab CEO sees developer tool bill increasing 100-fold Red Hat adds support for agentic AI development What’s new and exciting in JDK 26 Kill the loading spinner with local-first data and reactive SQL A networking revolution at AWS Tokenmaxxing is super dumb Hands-on with React, Supabase, and PowerSync How to add AI to an existing product (without annoying users) Your AI doesn’t need another database What happens when engineering teams reorganize around AI agents Python isn’t always easy When cloud giants meddle in markets 12 model-level deep cuts to slash AI training costs The best new features in Python 3.15 Teradata launches platform for enterprise AI agents moving beyond pilots Three skills that matter when AI handles the coding MongoDB targets AI’s retrieval problem
Notion courts developers with a platform for AI agents an...
2026-05-14 · via InfoWorld

Notion is expanding its collaborative workspace software with a developer platform for building AI-enabled workflows around enterprise data and workspace content.

The Notion Developer Platform adds custom code execution, database sync, external agent support, and workflow triggers, allowing developers and coding agents to extend Notion beyond its traditional role as a workspace app, the company said in a statement.

The launch comes as enterprises experiment with agentic AI but still struggle to give those systems access to the work context that is spread across business applications and internal systems. Notion is betting that developers will want to connect that scattered context to the workspace where teams already do much of their day-to-day work.

At the center of the release is Notion Workers, a hosted runtime for custom code. The feature underpins several of the platform’s new capabilities, including syncing external data, adding custom logic to agent tools, and responding to webhooks from other applications without requiring teams to manage their own servers.

“Write your logic in code and deploy it as a Worker,” Notion said. “It’s deterministic, so it’s more reliable than LLM reasoning, and a fraction of the token cost.”

Database sync, now in beta, can pull data from external systems with APIs into Notion databases. That would allow teams to bring in information from applications such as Salesforce, Zendesk, or internal databases and make it available to workflows and agents.

An External Agents API, currently in alpha, will allow third-party and internally built agents to work inside Notion. The company said it has partnered with Claude, Codex, Decagon, and others to make some agents available out of the box.

Developers will use a Notion CLI to sign into workspaces, act on Notion content, build and deploy Workers, and extend the platform programmatically. Workers are free during the beta period, but will run on Notion credits starting August 11.

Notion is also adding workspace-scoped OAuth, personal access tokens, a dedicated developer portal, rebuilt documentation, and updates to its MCP support.

Enterprise adoption hinges on governance

Analysts said the release gives Notion a bigger role to play in enterprise software stacks, provided it can meet CIO expectations around governance and production use.

“Notion Workers sit somewhere between low-code automation and lightweight serverless infrastructure,” said Tulika Sheel, senior vice president at Kadence International. “Unlike Zapier or Airtable, Notion is trying to combine AI agents, custom code execution, and workspace collaboration into a single environment.”

That could make the platform compelling for workflow-centric teams, Sheel said, although Microsoft Power Platform and cloud serverless offerings still have advantages in enterprise integration depth and operational maturity.

Notion’s Developer Platform marks the company’s entry into the emerging agent management platform market, said Nitish Tyagi, senior principal analyst at Gartner.

Its agent orchestration, custom tool execution, and data integration capabilities position Notion as a workspace-centric control layer for AI agents, he said. But rivals, including Atlassian, GitHub, JetBrains, and Tabnine, are already pushing deeper into context, governance, and multi-agent orchestration. “Notion’s feature set is not fundamentally new,” Tyagi said. “The success of the platform will depend less on what it offers and more on how well these capabilities perform in practice.”