Product design @NotionHQ. AI scout at @trueventures. Previously: co-founder @lexdotpage and @Every, first employee @Substack. Always: @SoniaBaschez
Los Angeles, CA
- Tweets 56,996
- Following 5,773
- Followers 50,473
- Likes 107,498
Pinned Tweet
Update: I’ve joined @NotionHQ!
I am ridiculously pumped to build the perfect space for people and agents to think together.
What an incredible time to join. The business is ripping, the team is insane (in a good way), and yet so much work remains ahead of us. It’s an honor and a thrill to be here and to help write Notion’s next chapter.
Some of you may be wondering, what does this mean for Lex and Roughdraft? Lex will be winding down by the end of the year, while Roughdraft will continue on as an independent open source project. I’ll give a more detailed update soon (especially for Lex users about the transition — I'll make sure you are taken care of), but the main message I want to share today is gratitude.
Thank you to @trueventures and all our investors, to the Lex team, to our customers and users, and to friends and family who supported us along the way. Also, a huge thank you to @ivanhzhao, @akothari, @mschoening, and everyone at Notion for bringing me aboard and making me feel at home.
Most importantly, thank you to @SoniaBaschez. When we sat down for dinner in August 2022 and you told me you’d support me spending nights and weekends on that crazy AI writing idea I had (with an infant baby girl at home, no less), we had no clue what the next four years would look like. We had no idea we’d get hundreds of thousands of users within weeks, or that Sequoia would put Lex on a market map. We had no idea ChatGPT was coming in a few months, or how AI would reshape the world. We had no idea Lex would become not just be a side quest at Every, but an independent company. All we knew was that we had a good feeling about it, and you were willing to bet on it.
Anyway, as you can tell, I am insanely excited for what comes next. Can’t wait to share some of the things we’re cooking up with you soon. And whether you love or hate Notion, I’d love to help make it better for you!
241
18
1,166
140,926
I have not seen near enough excitement about MCP Events developers.openai.com/plugin…
Right now, the only way most people's agents can wake up and do something is either A) cron, or B) you decide to message it
Event-driven triggers are a huge deal
85
77
1,084
76,408
Some use cases I am excited about:
- @mention your agent in a comment (Notion, Google doc/sheet, Figma, etc) and it replies or takes some action
- triage notifications from slack, email, linear, Notion, etc and alert you if something important comes in, or even get started on the next action for you if action is required
- when a new episode of your favorite pod is published get an alert and a quick personalized summary of what in it might be interesting to you
- notifs when PR checks in GitHub are finished
- you could have an external system as a subagent that could be long running and alert you when it’s done
9
3,817
Nathan Baschez retweeted
I’m running a universal memory for all of my AI platforms with @NotionHQ
I have this database connected to Grok Bot, Claude Code, Grok Build, and Meta Muse. They all have the below instructions and autonomously write to this database whenever something comes up that should be remembered. They all know they are sharing this database with other AI’s and that we are building a unified memory for all of them. They all know to check here when I ask them questions that might require context.
59
8
266
67,678
Notion is laser focused on performance and reliability improvements
I've heard from some friends they are starting to feel a difference! Which is great! But job's not finished :)
implemented postgres extended query protocol pipelining, makes queries at notion go about 50% faster
why? notion runs many queries in transactions so we can use pgbouncer txn pooling + SET LOCAL; many reads look like this:
await query(sql`BEGIN; SET LOCAL search_path = ...`)
const result = await query(sql`SELECT ...`)
// rare txns sometimes do more reads
await query(sql`COMMIT`)
pipelining which reduces network round trips from N → 1 for reads and N → 2 for writes (tho maybe its fine to pipeline COMMIT there also)
const results = await query(new ExtendedQueryPipeline([
sql`BEGIN`,
sql`SET LOCAL ...`,
sql`SELECT ...`,
sql`COMMIT`,
]))
ALT postgres queries at notion getting 30%-60% faster
5
1
72
8,048
Notion is great with agents.
Here's a prompt I've been working on that makes agents great with Notion: developers.notion.com/prompt…
Try it! We'd love feedback :)
9
15
215
31,375
4yo: “You know what a marshmallow and coffee cake party is?”
Me: “What?”
4yo: “It’s where you eat marshmallows and coffee cakes! And you celebrate that”
6
1
36
2,816
I think the ideal model router actually is just starting with a cheap model and teaching it to escalate as needed + using a more powerful model as a “checker” that also can escalate
Reminder that Jev is a "system one" model. It does not reason. It categorizes.
It is nearly impossible to know how "complex" a task is purely from a prompt. You need to understand the system the prompt is made in, the tools the agent has access to, and the complexity of what the agent has to work around to complete the work.
Jev has none of this context. Literally zero. It cannot know how hard it is to make a change in your codebase. If you ask an agent to "port this to Rust," it doesn't know if the codebase is a 100-line TypeScript file or if it's a million-line complex application. It doesn't know if your request to fix a bug touches complex pieces of your application or if it's a simple two-line change.
Jev is awesome, but it is not built for this. In order to know how much thinking a task requires, you have to think. Jev does not "think".
15
1
50
7,900