Notion Developers

218 posts

Notion Developers banner
Notion Developers

Notion Developers

@NotionDevs

Connect Notion to the tools you use every day.

Katılım Mart 2020
15 Takip Edilen19.1K Takipçiler
Notion Developers retweetledi
Kenneth Sinder
Kenneth Sinder@KennethSinder·
New @NotionDevs features hot off the press (JS SDK v5.14.0): - API to manage and query database views, including linked views. Great for automations & setting up new workspaces! - Status properties supported in API and @NotionHQ MCP ⤵️
Kenneth Sinder tweet media
English
4
7
37
3.3K
Notion Developers retweetledi
Jonathan Clem
Jonathan Clem@_clem·
New in the Notion CLI, `ntn`: The whole Notion API! And a skill so that your agents know how to use it. - Read the docs; this is alpha-y so auth is a little wonky. - Use `npx skills add makenotion/skills` to teach your agent about it!
Jonathan Clem tweet media
English
9
38
240
109.3K
Notion Developers retweetledi
Sarah Sachs
Sarah Sachs@sarahmsachs·
With the beauty of abstraction in MCP comes a lot of nerf’ing - way below the capabilities of our agents today. Some smart cookies at @NotionHQ (@goldmanem @MarissaJFelix and @akm_io ) talk through @NotionHQ journey with MCP and CLI.
Notion Developers@NotionDevs

MCPs were supposed to be the new universal plug for AI agents. So why are MCPs suddenly being dropped for the old school CLI? Eric Goldman (@goldmanem), MJ Felix (@MarissaJFelix), and Modi (@akm_io) dug out the signal from the noise on MCPs vs CLIs and how model capabilities are dramatically changing what’s possible under the hood, all from the frontier of of our team building real workflows with (and for 👀) agents. Some highlights: → MCP's promise was real — plug-and-play with just a URL. But it became a lowest-common-denominator abstraction that jammed product intent, workflows, and agent assumptions into one layer. → Models outgrew MCP faster than it could evolve. Early MCPs were simplified for weaker models. By the time teams shipped them, the models didn't need the guardrails. → Every MCP layer burns tokens. Viewing a long page costs 50k tokens through MCP. With a CLI, you pipe to head and grab what you need. → CLI is the new (old) frontier. Models are now strong enough to write code and compose tools directly with CLIs. But what are the downsides to that? → More tools, not fewer. Conventional wisdom said keep tool count low. We're moving toward agents that can handle hundreds of tools instead of a dozen. → Integrations will disappear. The future is agents writing scripts per workflow, talking directly to other agents, and using the same tools humans use. Oh...and pay attention. They may have let a few dev platform updates slip 👀

English
1
2
19
5.6K
Notion Developers retweetledi
OpenAI Developers
OpenAI Developers@OpenAIDevs·
Codex 🤝 @NotionHQ Meet us in NYC on March 17 for a night packed with: Codex demos. Practical workflows. Builders to meet and learn from. luma.com/52o30i5i
English
41
47
797
124.8K
Notion Developers
Notion Developers@NotionDevs·
MCPs were supposed to be the new universal plug for AI agents. So why are MCPs suddenly being dropped for the old school CLI? Eric Goldman (@goldmanem), MJ Felix (@MarissaJFelix), and Modi (@akm_io) dug out the signal from the noise on MCPs vs CLIs and how model capabilities are dramatically changing what’s possible under the hood, all from the frontier of of our team building real workflows with (and for 👀) agents. Some highlights: → MCP's promise was real — plug-and-play with just a URL. But it became a lowest-common-denominator abstraction that jammed product intent, workflows, and agent assumptions into one layer. → Models outgrew MCP faster than it could evolve. Early MCPs were simplified for weaker models. By the time teams shipped them, the models didn't need the guardrails. → Every MCP layer burns tokens. Viewing a long page costs 50k tokens through MCP. With a CLI, you pipe to head and grab what you need. → CLI is the new (old) frontier. Models are now strong enough to write code and compose tools directly with CLIs. But what are the downsides to that? → More tools, not fewer. Conventional wisdom said keep tool count low. We're moving toward agents that can handle hundreds of tools instead of a dozen. → Integrations will disappear. The future is agents writing scripts per workflow, talking directly to other agents, and using the same tools humans use. Oh...and pay attention. They may have let a few dev platform updates slip 👀
English
3
2
67
19.3K
Notion Developers retweetledi
Notion Developers retweetledi
Guillermo Rauch
Guillermo Rauch@rauchg·
Vercel now powers the Notion agent platform. Not only are they a great company and product I use daily, I think they're going to be one of the big winners of the agent era. The main 'runtime' of an agent is English (natural language) documents and specs. The other ingredient is access to data and integrations. Notion is at the center of both.
Vercel@vercel

Vercel powers @NotionHQ's developer platform. Notion Workers use Vercel Sandbox to safely run code, giving agents the power to sync data, trigger automations, and call any API. vercel.com/blog/notion-wo…

English
31
23
424
72.8K
Notion Developers retweetledi
Kenneth Sinder
Kenneth Sinder@KennethSinder·
Proud to signal-boost the latest update to the @NotionAPI: #march-11-2026" target="_blank" rel="nofollow noopener">developers.notion.com/page/changelog… - New `2026-03-11` version w/ some renames (to make room for some awesome upcoming features!) - MCP tools to create/update database views - Improved modes for the markdown-based page update API
English
4
2
28
4.4K
Notion Developers retweetledi
Geoffrey Litt
Geoffrey Litt@geoffreylitt·
✨New demo: what if vibe coding felt more visual? @brian_lovin @maryrosecook and I did a game jam using Notion as our "IDE": launching Cursor agents from a task board, and making a custom image for each task 😎 The demo shows 3 ideas for the future of agents: 1) Agents should collaborate across apps. Each app has its focus--Notion AI is good at drafting specs and organizing tasks; Cursor is good at coding. So let them specialize! Today we're launching a new integration where Notion AI can kick off Cursor Cloud Agents to do coding tasks. The Cursor API accepts natural language prompts, so I think of this as "cross-app sub-agents" -- it's kinda cute how it resembles humans hiring outside contractors 😊 BTW: the parallelism of cloud agents is incredibly freeing for creativity, but it also creates a new problem: sooo much work to keep track of! Which brings us to the next idea... 2) Agent orchestration is a data visualization problem. A powerful frame for designing agent UIs is to think of the chat transcripts as the "raw data" and ask: what visual projections might help people make sense of this data at scale? We need to engage our human GPUs -- our visual processing -- to understand what the computer GPUs are doing for us! One thing we can do is use AI to populate traditional UIs like progress bars and status updates. But there are also new possibilities now... For example: when you have a lot going on, it can be hard to identify tasks just by text titles. So we tried generating an AI image for each task -- turns out this helps a lot by giving it a unique visual identity! And of course, it also just makes it super fun to build with friends 😃 Speaking of friends... 3) The future of coding is collaborative. Sometimes it feels like IC engineers are being reduced to middle managers: shuffling information between the team's context and the coding agents that they individually manage. The solution: bring all the people and agents into one shared space, with shared context and visibility! In the video you can get a glimpse of how this feels. Mary, Brian and I record ourselves chatting about ideas, and then we use AI to turn that conversation into a list of tasks on a shared board. As the ideas get built in parallel, we can all monitor progress and review the work together, nothing is siloed. My main takeaway from this game jam was: damn, creativity with friends, at the speed of conversation, is incredibly fun. --- Our goal here is to let anyone use Notion as a fun and creative "software factory" to build software together with your team. Give the Cursor integration a shot and let us know what you think! (AI Image gen in Notion isn't GA yet, but coming soon and already out to some users) And let me know if you'd want a template or more detailed instructions on the setup we showed in this demo...
English
28
37
279
74K
Notion Developers retweetledi
Zach Tratar
Zach Tratar@zachtratar·
Announcing MCP & API support for Notion AI Meeting Notes! Install in 8 seconds. 🪄 Turn meetings into code, fast 🧑‍💻 Vibe code apps that use meeting notes data 🤖 Query meetings quickly in ChatGPT + Claude 🔀 Integrate your meetings data with other apps
Zach Tratar tweet media
English
22
33
355
57.3K
Notion Developers retweetledi
Michael Pfister
Michael Pfister@pfista·
I just open sourced the @NotionHQ workers for @toggl and @mercury invoicing now you can automate your monthly invoices too i'll be adding more workers to this repo as I automate the rest of my business into oblivion link below
Michael Pfister tweet media
Michael Pfister@pfista

I fully automated monthly client invoicing with @NotionHQ custom agents and workers Every month my custom agent: - Pulls billable hours from @toggl, my team's time tracking app - Calculates $ amounts accurately with Python in a @vercel sandbox - Creates an invoice in @mercury for the correct customer with the right $ amounts, dates, etc - Drafts an email to my client with a link to the invoice - Pings me on slack that the invoice is ready to review All I have to do is press send No reason I couldn't automate this fully. I will eventually once I trust it's 100% accurate.

English
8
3
36
6.3K