Sabitlenmiş Tweet
Introducing: the Notion Developer Platform
New building blocks that help you (and your coding agents) sync any data source, build any tool, and orchestrate any agent.
Follow along 👇 x.com/i/broadcasts/1…
English
Notion Developers
642 posts
Notion Developers
@NotionDevs
Any data. Any tool. Any agent. All in Notion.
Katılım Mart 2020
24 Takip Edilen26.8K Takipçiler
Notion Developers retweetledi
"I think it's important for people to understand how code works."
Geoffrey Litt's Design Eng track keynote is live now:
youtube.com/watch?v=WkBPX-…
Thank you @NotionHQ for supporting his incredible work and thank you Geoff for kicking off WF26 for our Design Engineers!
YouTube
Geoffrey Litt@geoffreylitt
Hot take: I think it's still important to understand the code that our agents write! In this mega thread (based on my AIE talk today), I will explain why that's the case, and show some ideas for how to efficiently understand code. Alright, let's dive in. 1/
English
Today we're shipping spatial context.
This lets you draw directly on your screen + pass it as context to the model.
AI can easily analyze screenshots. But, it has no idea where exactly you want it to look. Now you can just show it.
It's very intuitive.
Demo:
English
.@mschoening, Notion’s Head of Product, believes AI chat isn’t as overrated as the timeline makes it out to be.
He has two main reasons:
> Version control
> Latency
"I feel like I haven’t been in a flow state in the last like 12 months ever since the models got really good” because I'm constantly jumping between tasks.
With chat, “if I I want to go back in time, I can just scroll back up.. and theoretically fork off from there and keep going.”
And realistically, latency still matters.
With current inference speeds, “you don’t get direct manipulation. If we made UIs today that are about direct manipulation, you’d see the beach ball every time"
But with these constraints, he thinks “chat is the thing that helps with this”
English
And there’s still more left we haven’t talked about ;)
Check out the full report for more context:
notion.com/lp/ai-engineer…
English
All of this has added up to a change in how organizations are now operating.
The good news is that basically every respondent (97%) is feeling a positive downstream effect of AI in the org. But there is a cost to every dalliance.
93% are also feeling negative downstream effects, the most common being a widely discussed erosion of deep technical skills and understanding. All of the consequences of infinitely cheap code generation show up here.
English
As a result, we are now seeing evals make a larger impact in how people are approaching their AI usage, with 56% of responders prioritizing quality right above cost at 48%.
🚨 Another potential narrative violation: almost 50% say they’re using RAG of some sort.
English
One large industry change we’ve noticed is the increase in open weight usage, but they are not being used independently.
Today open source is best thought of as a helpful companion to closed source but not yet a direct replacement. Of the 54% using open-weight models, either out of the box (37%) or fine-tuned (17%), >90% are also using closed models.
Open vs. closed is actually only a primary consideration for 5%. The most important quality by far is… quality, followed by agentic capabilities and then cost.
English
Vibe coding at an organizational level is out. Value coding is in, especially as model improvements flatten out and prices continue to go up.
40% say cost regularly shapes how ambitiously they use AI, and 36% say it sometimes does. All in all, three-fourths are adjusting their AI usage based on cost. This sounds… obvious, but if you can put yourself in your own shoes just 12 months ago, it was anything but.
English
Agents are only as good as their guardrails.
Plan modes, clearing context windows, and specific model choices can make an impact, but 61% of respondents say that agent hallucinations frustrate them the most.
Keeping a human in the loop is still relevant, but that interception point seems to be getting pushed out further as model capabilities have been increasing.
English
We partnered with @vercel and @AmplifyPartners to survey over 1,000 engineers building with AI and get you the inside scoop. What’s in, what’s out, and how the already fast moving AI space is changing.
We cover agent usage, model preference, open weight, evals, and more.
Lets dive in! 🧵
English
If 2025 was the year of agents, 2026 has been all about integrating agents in the way you work, from building infrastructure to taking advantage of their larger context windows.
Among teams using agents, 90% say those agents can write data, compared with 52% last year. But the majority still require a human in the loop.
English
The other day @colebemis asked me if I thought Notion was a cult. My answer was I’m so deep I have no way to answer that as a reliable narrator.
But that’s kind of the point. To work here is to believe it. Which means every conversation and debate is high trust, because we all have the same red-stained teeth.
Camille Ricketts@camillericketts
In our experience, Kool-Aid flowing is one of the best indicators of real magic at a company. For all the folks picking where to go next out there, here’s what we look for: • Evidence they’re winning. Revenue definitely. But also early headliner customers (Turbopuffer, Baseten, Stripe are all great at highlighting their’s), known talent on the early team (Pierre Computer, OpenAI, Anthropic, Thinking Machines all have notably stacked early crews), and (especially if pre-revenue) accolades that industry leaders pay attention to (Physical Intelligence winning the Robot Olympics). • A mission that matters to you. You’ll feel pride in your bones making this thing happen. • Zaggy vision for the world. The best companies to join are non-consensus and right. Industry experts laughed Etched out of the room. Anthropic was seen as too soft and safety-focused. Do you believe in the future a company is building? • Founder aura. Do you feel the pull to impress them and be in their midst? That counts for a lot… because you will have to be. • Internal stage for excellent work. Does this company have a way they regularly elevate folks inside for doing interesting things, making things, doing deals? How high is the bar for what they feature at All Hands? What earns a Slack shout out from the CEO? Will you have constant visibility to learn from your highest performing teammates - and maybe become one, too? • External platforms encouraged. Do you see people at the company tweeting about their work? On stages at conferences? Hosting their own events? Writing blog posts? Think @jeff_weinstein at Stripe. @ryolu_ at Cursor. @sarahmsachs at Notion. @oneill_c at Baseten. It’s a signal the company invests in people and their ideas. • Rituals. Raises eyebrows on the outside, beloved on the inside. The best kind of cult. Vercel wears all black. Hundreds of cursors swarm Figma All-Hands slides as they’re being presented. Stripes used to run up Bernal Hill and played Werewolf in the evenings. Sub-20 Notion ate heaping piles of pasta every Friday at the same restaurant (and yet never needed a nap). Memories are sticky. • Strong merch game. Unusual swag people actually want to wear - a sign of deeper care and creativity. Our recent favorite: Gumloop has people bring in their favorite they’d wear everyday if they could and get it embroidered on the spot. • Culture heads indulged. Those folks who want to make the place awesome are told to “go for it!” Ben Barry churning out posters at early Facebook (that we can all still recite). Back in the day Dropbox’s famed Blackops squad stocked in-office karaoke studios, made an employee holiday catalog full of odd offerings. Good energy begets good energy. • Other people are telling the story. The most honest reviews you’ll get of a place are outside-in, but they come in all forms. Andrej Karpathy tweeting. 100 community members sharing what they built. Customers name dropping the company on stage. The timeline’s inner circle commenting on product launches. See: who responded when Midjourney Medical went live. Join a company that makes friends. Its network will be yours.
English
This album is special to me. It was our "theme song" for the @NotionHQ Academy about 1 year ago, and was the answer to “what should this whole thing feel like.”
It's Red Garland’s Piano- we listened to it on the set before filming, and as we wrote the scripts.
Makes work more fun to have a theme song for your project. Nostalgic about this one.
English
With Can connect access, shared Workers show up in the Connections panel for Custom Agents.
With Full access, shared Workers show up in the Connections panel, and in your Developer Portal and CLI.
English
There are two levels of access:
Full access: Your teammate can edit the Worker—update code, deploy changes, and manage it with you.
Can connect: Your teammate can use that Worker in their own Custom Agents, but can’t change the code. Think of it like a prebuilt MCP connection: someone else built it, you just plug it into your agent.
English
You can now share your Notion Workers.
Build and iterate on Workers with your team. Or share one so teammates can connect it to their own Custom Agents.
Free to try while Workers is in beta.
English
Notion Developers retweetledi
Introducing Ship OS: The agent-native way to ship software.
Run your entire product development cycle in Notion, from customer feedback to a merged PR.
Agents handle the triaging, routing, and summarizing. Your team handles the judgment calls.
Set up Ship OS → notion.com/ship-os
English