Simon Last
2.1K posts
It took us two years to grow from $10 mm to $100 mm in Annual Recurring Revenue and 15 months to reach $200 mm. Nine months later, we crossed $300 mm. Vanta’s growth rate increased each of the past four quarters – compounding really is the eighth wonder of the world!
“But wait,” you might be thinking. “How does a software company founded before 2022 *increase* its growth rate?” Narrative violation!
English
Models are changing really fast, often in ways that will break your product and technical assumptions.
There's no way around this – the only way forward is to relentlessly iterate to make sure you're on target with what's available now, and what you can see on the horizon.
The good news is, it's easier than ever to do this if you properly apply coding agents!
swyx 🇸🇬@swyx
finally: @simonlast + @sarahmsachs on Latent Space! Notion has rebuilt Notion AI 5 times. This is the first time Simon has told the entire story. I've been trying to do this interview for ~3 years. We run @latentspacepod on Notion since inception, as does every other top tech company. Notion is one of the top ~3? knowledge work tools in the world, crossing 100M users in 2024 and now shipping the AI productivity suite that @ivanhzhao wants to be "steel and steam for organizations" — the backbone of a new Industrial Revolution of Infinite Minds that will change the world.
English
@tanaypadhi I'm definitely checking on the agents. While I'm awake, I check as often as I can. While I'm asleep, they go fully autonomous and have some chance of getting stuck or going off track.
English
The less fatuous version of this question, how do you think about educating it on the right checkpoints to bring you into the loop?
Put another way, you likely wouldn’t have a human engineer work on something without any oversight or check-ins at all for more than a couple of days
English
@NotionHQ @simonlast @saranormous If he could provide examples of exactly what use-cases/problems solved, that would be fantastic!
English
Our co-founder, Simon’s record is letting a coding agent run for 13 days straight.
His bedtime routine now includes giving his agents enough work to keep running until breakfast 🍳
@simonlast
@saranormous
English
@NotionHQ @simonlast @saranormous Genuinely curious what those use cases are and how you prompt in a way there’s enough work until breakfast? How exactly does anyone do that?
English
@NotionHQ @simonlast @saranormous Did you prompt the agent to sleep for 10 mins every time it ran a command?
Hard to believe a 13 day run could produce anhthing worthwhile
English
Some notes on how I got a coding agent to work for 13 days straight:
Self-verification: the agent needs to be able to end-to-end verify everything itself. Design efficient testing layers that make sense for your project, and make sure the agent can effectively loop on them to prove correctness.
Write spec documents: work with the agent to fully specify goals, full implementation details, and verification in a document. It's almost always fruitful to iterate on this multiple times. This could be anywhere: a Notion page, or just a simple .md file.
Use a running to-do list: break down complex work into a to-do list that you can see and edit. As you think of more things for it to do next, you can just add more to-dos. This could be anywhere: a page or database in Notion, or a .md file.
Adversarial review: as a step in the process, the agent should ask another agent to review the spec and implementation and make sure there are no gaps. Force the agent to loop on this until it's totally aligned. This can use sub-agents if that's supported, or you can design a simple CLI that calls another agent. The key thing is to invoke a fresh agent context.
This was for a prototype of a new product. It's easier to do all of this on a small codebase, but the principles work anywhere.
Notion@NotionHQ
Our co-founder, Simon’s record is letting a coding agent run for 13 days straight. His bedtime routine now includes giving his agents enough work to keep running until breakfast 🍳 @simonlast @saranormous
English
Thrilled to join @NotionHQ!
It’s an exciting moment to be building tools for the future for everyone. I’ve used Notion for over a decade and admired what this team has built for a long time, so this one was an easy decision.
Really grateful (and very excited) to be here. Let’s go 🧱
English
Simon Last retweetledi
The loudest story about AI is a lonely one. One person with an army of chatbots. Other humans are friction.
That gets the future wrong. The best things aren’t built alone.
In a moment of change, we want to remind the world (and ourselves) what Notion stands for:
— Think Together
English
Sharing a few of my favorite prompt snippets for coding:
For iterating on a spec:
Please step back and think again. How can we make this SIMPLER and DUMBER while still achieving our goals?
For planning:
Please research the codebase to make sure you fully understand how stuff currently works, and make a detailed plan to achieve the above.
Your plan must be fully fleshed out and include only concrete actions such as editing files and running commands (ie. your plan cannot include actions like “read this file”).
Your plan must also include how you will verify it is correct yourself, end-to-end.
Don’t make any code changes yet. Research now as much as you need and then chat back with your full plan when ready.
For debugging:
Please think carefully and truth seek. Don't just blindly re-run things and hope they will work. Read the code, and liberally add temporary logging statements anywhere in the codebase to verify logic works as you expect (just remember to not commit them). Dig deep and take the time to really figure out the root causes of problems.
English
Simon Last retweetledi
Our cofounder @SimonLast hasn't written a line of code since last summer.
With custom agents running while he sleeps, entire products get built without him touching the keyboard.
Custom agents run his inbox. Route bugs. File tasks. Search across Slack, Drive, and Notion—and find him answers, not links.
He sat down with @Saranormous on @NoPriorsPod to share what it looks like when the entire company runs on agents.
English
MCP sucks honestly
It eats too much context window and you have to toggle it on and off and the auth sucks
I got sick of Claude in Chrome via MCP and vibe coded a CLI wrapper for Playwright tonight in 30 minutes only for my team to tell me Vercel already did it lmao
But it worked 100x better and was like 100LOC as a CLI
Morgan@morganlinton
The cofounder and CTO of Perplexity, @denisyarats just said internally at Perplexity they’re moving away from MCPs and instead using APIs and CLIs 👀
English
@simonlast 1) i dont want magic link auth ever when we have saml configured
2) it still forgets the nextUri/redirectUri value in some cases
i use notion once a month so couldnt tell you how to repro (2) or how regular it is
English
Simon Last retweetledi
Our cofounder @simonlast built the first Custom Agent at Notion. It had one job: route product feedback.
Then he gave it a blank page and let it figure out the rest.
Now the whole company relies on it 👀
English
With Notion Workers, you can build a custom integration that connects your custom agent to pretty much anything, usually in under 10 minutes!
Jonathan Clem@_clem
Alongside Custom Agents, we're also quietly releasing an "extreme pre-alpha" of something called Notion Workers. I joined Notion dreaming we would one day make it a developer platform, and this is just the start! github.com/makenotion/wor…
English
Custom agents are here – I'm so proud of the team for this launch!
My personal favorite: I set up an email triage custom agent a few months ago and it completely solved email for me. I get a daily recap of what I need to see, and anything I don't is automatically archived.
Notion@NotionHQ
Introducing Custom Agents. The AI team that never sleeps 🌙 They’re autonomous, built for teams, and easy for anyone to build. Give them a job, set a trigger or schedule, and they'll get it done 'round the clock.
English